git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill's primary purpose is a security feature intended to prevent accidental execution of destructive Git operations. No malicious patterns or data exfiltration attempts were detected.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute
chmod +xon the bundled hook script (scripts/block-dangerous-git.sh) to make it executable. This is an expected step for installing local tool hooks. - [COMMAND_EXECUTION]: The skill modifies the agent's configuration files (
.claude/settings.jsonor~/.claude/settings.json) to register the hook script. While this modifies agent behavior across sessions, it is the documented and necessary procedure for the skill's functionality.
Audit Metadata