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 +x on 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.json or ~/.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
Risk Level
SAFE
Analyzed
Jun 13, 2026, 09:28 AM
Security Audit — agent-trust-hub — git-guardrails-claude-code