Skills
skills/marcioaltoe/skills/git-guardrails-claude-code/Gen Agent Trust Hub

git-guardrails-claude-code

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to enhance safety by intercepting potentially destructive git commands like 'push --force' or 'reset --hard' and blocking them via a local hook.
  • [SAFE]: The provided script scripts/block-dangerous-git.sh safely handles input by using jq for JSON parsing and does not execute any part of the command it inspects.
  • [SAFE]: Configuration changes are limited to the intended application settings (.claude/settings.json), and no external network activity or unauthorized data access is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:35 PM
Security Audit — agent-trust-hub — git-guardrails-claude-code