topic
AI Security
1 post tagged AI Security.
AI Security4 min read
How Claude's web_fetch Tool Leaked User Data, One Letter at a Time
A researcher turned a fake coffeeshop CAPTCHA into a working exfiltration channel against Claude's memory — by getting the AI to spell out a name one hyperlink at a time. Here's the mechanism, the fix, and why it matters for anyone shipping tool-using agents.
- ai-security
- prompt-injection
- claude
- agentic-ai
- llm-safety