git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a security guardrail designed to intercept and block destructive Git commands (like push, reset --hard, etc.) before they are executed by the agent.
- [COMMAND_EXECUTION]: The provided bash script uses standard, non-malicious utilities (jq, grep) to parse input and check against a list of blocked patterns. It does not perform unauthorized shell execution.
- [PERSISTENCE]: The skill modifies agent-specific configuration files (.claude/settings.json or ~/.claude/settings.json) to install the hook, which is the explicitly documented and intended purpose of the skill.
Audit Metadata