AWS Fixes Data Exfiltration Attack Angle in Amazon Q for Business. An indirect prompt injection (where the AWS Q bot consumes malicious instructions) could result in Q outputting a markdown link to a malicious site that exfiltrated the previous chat history in a query string.
Amazon fixed it by preventing links from being output at all—apparently Microsoft 365 Chat uses the same mitigation.
Recent articles
- Live blog: Claude 4 launch at Code with Claude - 22nd May 2025
- I really don't like ChatGPT's new memory dossier - 21st May 2025
- Building software on top of Large Language Models - 15th May 2025