Skills
Navigate
skills/boom-vitt/skills-thai/git-guardrails-claude-code/Gen Agent Trust Hub

git-guardrails-claude-code

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill involves making a script executable via chmod +x and running validation tests, which are standard procedures for installing command-line utilities.
  • [SAFE]: The skill modifies agent configuration files (.claude/settings.json or ~/.claude/settings.json) to register a PreToolUse hook. While this persists across sessions, it is the primary stated purpose of the skill to provide continuous git command protection.
  • [SAFE]: The provided protection script (scripts/block-dangerous-git.sh) safely extracts command inputs using jq and performs pattern matching via grep to identify and block destructive operations, following standard input validation practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 12:52 PM
Security Audit — agent-trust-hub — git-guardrails-claude-code