Simon Willison’s Weblog

Subscribe

Monday, 12th January 2026

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]

Superhuman AI Exfiltrates Emails (via) Classic prompt injection attack:

When asked to summarize the user’s recent mail, a prompt injection in an untrusted email manipulated Superhuman AI to submit content from dozens of other sensitive emails (including financial, legal, and medical information) in the user’s inbox to an attacker’s Google Form.

To Superhuman's credit they treated this as the high priority incident it is and issued a fix.

The root cause was a CSP rule that allowed markdown images to be loaded from docs.google.com - it turns out Google Forms on that domain will persist data fed to them via a GET request!

# 10:24 pm / security, ai, prompt-injection, generative-ai, llms, exfiltration-attacks, content-security-policy

2026 » January

MTWTFSS
   1234
567891011
12131415161718
19202122232425
262728293031