git-guardrails-claude-code

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to make a local shell script executable (chmod +x) and configure it as a hook. This is the intended primary purpose of the skill to provide Git safety guardrails.
  • [SAFE]: The shell script (scripts/block-dangerous-git.sh) performs local string matching on Git commands to prevent destructive operations. It does not contain any exfiltration, persistence, or privilege escalation patterns.
  • [SAFE]: The configuration changes target standard Claude Code settings files (.claude/settings.json) to register the local hook. This behavior is transparent and aligned with the skill's description.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 10:23 AM
Security Audit — agent-trust-hub — git-guardrails-claude-code