git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill installs a Bash script that uses the jq utility to parse agent tool inputs and intercept dangerous Git commands before they are executed.
- [SAFE]: The skill modifies agent-specific settings files (~/.claude/settings.json) to persistently register the guardrail hook, which is the stated purpose of the skill and does not exhibit malicious behavior or unauthorized data access.
Audit Metadata