Malicious .git Config Vulnerabilities Let AI Coding Agents Run Attacker Code

Manifold Security disclosed eight vulnerabilities across seven CLI AI coding agents including Claude Code and Cursor, where malicious .git config entries like core.fsmonitor can trick agents into executing attacker-controlled code on developer machines.

2026-09-03 ~ 2026-09-03 · 2 related posts

• Malicious .git configs can make Claude, Codex, Cursor AI agents run attacker code — jedisct1 · 2026-09-03
• Malicious .git configs make Claude Code, Codex, Cursor run attacker code pre-trust-prompt — Thionne_WTZ · 2026-09-03