As cited
Copy frozen at (site build).
ai security
Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code
Manifold Security disclosed eight security flaws across seven command-line artificial intelligence (AI) coding agents in which a repository's Git configuration can name a command that the agent executes on the developer's machine without a sandbox or approval prompt. Four of the affected agents remained unpatched at the time of disclosure. Exploitation requires the repository to be present on the developer's system.
Why it matters: Developers using Claude, Codex, Cursor, and other AI coding agents face remote code execution (RCE) risk when cloning or working with malicious repositories, as the agents run attacker-controlled commands with user privileges.
- Source published
- First seen by Cybersecurity Tracker