Friendly Fire: AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It
- Posted on July 9, 2026
- By The Hacker News
- 0 Views
- 1 min read
Friendly Fire: AI Agents Built to Catch Malicious Code Can Be Tricked Into Running It
AI Now’s Friendly Fire PoC shows Claude Code and Codex running README-planted payloads on hosts when autonomous command approval is enabled.
