git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell scripts and configuration modifications to implement a security feature.
- The script
scripts/block-dangerous-git.shis designed to be installed as aPreToolUsehook in Claude Code settings (.claude/settings.json). - It requires the user to run
chmod +xto make the script executable, which is standard for local tool installation. - The script uses
jqto parse tool input andgrepto validate commands against a predefined list of destructive Git patterns (e.g.,git push,git reset --hard). - There is no evidence of network exfiltration, credential harvesting, or obfuscation. All operations are local to the user's repository or home directory.
Audit Metadata