The safety layer for vibe coding and AI coding agents: flag risky changes and restore project files, including uncommitted work, to their pre-session state.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts — it cannot prove the absence of malicious code.
The safety layer for vibe coding and AI coding agents: flag risky changes and restore project files, including uncommitted work, to their pre-session state.