Skills
Navigate
skills/visualxintelligence/mattpocok-skills/git-guardrails-claude-code/Gen Agent Trust Hub

git-guardrails-claude-code

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill's primary function is defensive; it is designed to protect the user's repository from accidental destructive actions by the AI agent.
  • [COMMAND_EXECUTION]: The skill sets up a local bash script (scripts/block-dangerous-git.sh) to be executed as a 'PreToolUse' hook. This script validates Git commands against a list of dangerous patterns before they are allowed to run. The script relies on the standard jq utility to parse JSON inputs from the agent environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 12:34 AM
Security Audit — agent-trust-hub — git-guardrails-claude-code