git-guardrails-claude-code

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPERSISTENCE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use chmod +x on a bundled bash script (scripts/block-dangerous-git.sh) after copying it to the local or global .claude/hooks/ directory. This is necessary for the script to function as a hook.
  • [PERSISTENCE]: The skill modifies either a project-level (.claude/settings.json) or a global (~/.claude/settings.json) configuration file to register a PreToolUse hook. This ensures the guardrail script runs automatically before the agent executes bash commands, which is the stated and intended purpose of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 07:50 AM
Security Audit — agent-trust-hub — git-guardrails-claude-code