Malicious Git Configurations Turn AI Coding Agents Into Silent Execution Engines

Malicious Git Configurations Turn AI Coding Agents Into Silent Execution Engines

Researchers from Manifold Security revealed that malicious .git/config files can force AI coding agents like Claude Code and Cursor to execute attacker commands before any trust prompt or sandbox engages. The GitSpawn flaws affect multiple popular tools and bypass typical permission models by abusing legitimate git features such as core.fsmonitor. Vendors have issued patches but several paths remained open at disclosure. Organizations must now r…

Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code

Manifold Security has disclosed eight security flaws across seven command-line AI coding agents in which a repository's own Git configuration names a… Read more → The post Malicious .git Configs Can Make Claude, Codex, Cursor, and Other AI Agents Run Attacker Code appeared first on IT Security News.

Researchers easily trick Fortune-500 companies' AI agents into running arbitrary code — supply-chain attack via llms.txt guidance file illustrates how data has become code

Researchers easily trick Fortune-500 companies' AI agents into running arbitrary code. This supply-chain attack, done via using data in public llms.txt guidance files, illustrates the dangers of data becoming code.