git-guardrails-claude-code

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill installs and configures a local bash script (block-dangerous-git.sh) as a PreToolUse hook within the Claude Code platform settings to intercept and validate Git commands.
  • [SAFE]: The use of chmod +x is limited to the skill's own bundled script to enable its execution as a guardrail, which is standard behavior for this utility.
  • [SAFE]: The modification of platform configuration files (.claude/settings.json or ~/.claude/settings.json) is necessary and intended for the skill's primary function of providing persistent Git guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 06:43 AM
Security Audit — agent-trust-hub — git-guardrails-claude-code