Manifold Security found eight vulnerabilities in seven AI CLI coding agents that execute attacker code injected via a malicious .git/config when the agents automatically invoke Git. This turns cloning

Manifold Security found eight vulnerabilities in seven AI CLI coding agents that execute attacker code injected via a malicious .git/config when the agents automatically invoke Git. This turns cloning any untrusted repository into potential remote code execution and undermines trust in AI-assisted development. # AiSecurity # SupplyChainSecurity # DevSecOps https:// cyberworldops.eu/en/git-turned -

1 reportother

Claim audit

No BS check run yet — press ⚖ to extract this story's claims and verify them against independent sources.

All coverage

Manifold Security found eight vulnerabilities in seven AI CLI coding agents that execute attacker code injected via a malicious .git/config when the agents automatically invoke Git. This turns cloning

mastodon:infosec-exchangeother27d ago kagi ↗

Manifold Security found eight vulnerabilities in seven AI CLI coding agents that execute attacker code injected via a malicious .git/config when the agents automatically invoke Git. This turns cloning any untrusted repository into potential remote code execution and undermines trust in AI-assisted development. # AiSecurity # SupplyChainSecurity # DevSecOps https:// cyberworldops.eu/en/git-turned -