Defensive AI Agents Can Be Hijacked for Remote Code Execution

AINowInstitute · x · 2026-07-08

AI Now Institute has published a proof-of-concept vulnerability research named "Friendly Fire". The study reveals that defensive AI agents like Claude Code and Codex can be maliciously hijacked to trigger Remote Code Execution (RCE) during security scans.

Related event: Research Reveals Defensive AI Agents Vulnerable to Hijacking(4 posts)→

Original post →

More from coding & agent

coding & agent channel →