topic
LLM Safety
2 posts tagged LLM Safety.
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
AI Security4 min read
Opus 4.6 Survived 6,000 Injection Attacks: Lessons for Agentic Finance
A public red-team challenge threw 6,000 email-based prompt injection attempts at a Claude Opus 4.6 agent — and nobody cracked it. Here's what builders of AI-driven financial systems should take from the result.
- prompt injection
- ai agents
- llm safety
- agentic finance
- claude opus