Simon Willison’s Weblog

Subscribe
Atom feed for claude-cowork

2 posts tagged “claude-cowork”

2026

Claude Cowork Exfiltrates Files (via) Claude Cowork defaults to allowing outbound HTTP traffic to only a specific list of domains, to help protect the user against prompt injection attacks that exfiltrate their data.

Prompt Armor found a creative workaround: Anthropic's API domain is on that list, so they constructed an attack that includes an attacker's own Anthropic API key and has the agent upload any files it can see to the https://api.anthropic.com/v1/files endpoint, allowing the attacker to retrieve their content later.

# 14th January 2026, 10:15 pm / security, ai, prompt-injection, generative-ai, llms, anthropic, exfiltration-attacks, ai-agents, claude-code, lethal-trifecta, claude-cowork

First impressions of Claude Cowork, Anthropic’s general agent

Visit First impressions of Claude Cowork, Anthropic's general agent

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.

[... 1,850 words]