git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill installs a bash script (
scripts/block-dangerous-git.sh) designed to intercept and validate shell commands before execution. This is the core functionality intended to provide safety guardrails. - [PRIVILEGE_ESCALATION]: The instructions require the user to run
chmod +xon the hook script. This is a standard requirement for enabling script execution in the host environment and is restricted to the specific script provided. - [PERSISTENCE]: The skill modifies the agent's configuration file (
~/.claude/settings.jsonor.claude/settings.json) to register a persistent hook. This behavior is documented as the standard method for enforcing safety policies across agent sessions.
Audit Metadata