Cybersecurity

Top AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It

Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker's code on your own machine instead.

Source The Hacker News AI Summary Updated 2h 51m ago

Story intelligence Beta

Freshness Fresh Updated 2h 51m ago

Confidence Checking

Coverage Checking

Views New Be the first to read

Read time 1 min ~60 words

AI Summary

Ask an AI coding agent to scan open-source code for security holes, and it might run the attacker's code on your own machine instead. That is the finding in a proof-of-concept published Wednesday by the AI Now Institute, an attack it calls "Friendly Fire." It works against Anthropic's Claude Code and OpenAI's Codex when either is running in an aut…

Read full article on The Hackernews

AI summaries can be wrong sometimes—always verify important details using the source article.