git-guardrails-claude-code
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill installs a shell script (
scripts/block-dangerous-git.sh) and configures it as aPreToolUsehook within the Claude Code settings (.claude/settings.json). This script is executed by the agent platform to validate shell commands before they are run. - [SAFE]: The included script is a benign security utility that performs simple string matching against a blacklist of Git commands to prevent accidental data loss or unauthorized remote pushes. It contains no network operations, obfuscation, or sensitive data access.
- [EXTERNAL_DOWNLOADS]: The skill does not perform any external downloads; the hook script is bundled directly with the skill and is intended for local installation.
Audit Metadata