Skills
Navigate
skills/michaeltarasov02/skills/git-guardrails-claude-code/Gen Agent Trust Hub

git-guardrails-claude-code

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill involves the creation and execution of a local shell script (scripts/block-dangerous-git.sh). This script is used as a 'PreToolUse' hook to validate commands before they are executed by the agent. The script uses jq to safely parse input and grep to match against a hardcoded list of restricted patterns.
  • [EXTERNAL_DOWNLOADS]: The shell script depends on the jq utility being present on the host system. It does not download any external code or scripts from the internet.
  • [SAFE]: The skill follows security best practices by prompting the user for the installation scope and providing clear instructions for manual configuration of settings and file permissions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 12:22 PM
Security Audit — agent-trust-hub — git-guardrails-claude-code