git-guardrails-claude-code

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONPERSISTENCE
Full Analysis
  • [SAFE]: The skill is designed as a security guardrail to prevent the AI from performing unintended destructive actions within a Git repository.\n- [COMMAND_EXECUTION]: The skill provides a bash script (scripts/block-dangerous-git.sh) and instructs the user to set execution permissions using 'chmod +x'. This script uses 'jq' to parse tool invocation data and validate the proposed commands against a list of dangerous patterns.\n- [PERSISTENCE]: The skill persists its protective behavior by modifying the agent's configuration files ('.claude/settings.json' or '~/.claude/settings.json') to register a PreToolUse hook, ensuring the check runs for all subsequent tool calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 09:23 PM
Security Audit — agent-trust-hub — git-guardrails-claude-code