repo-guardian

Detect security risks in Claude Code repositories by analyzing git hooks and configurations.

1|Updated Mar 13, 2026
One-click install
npx skills add https://github.com/traygerbig/clawhub-skills --skill repo-guardian
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: repo-guardian
Source: https://github.com/traygerbig/clawhub-skills/tree/main/security-devops-pack/repo-guardian
Command: npx skills add https://github.com/traygerbig/clawhub-skills --skill repo-guardian

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill identifies potential security threats in repositories before Claude Code processes any files, mitigating risks from repository-borne attacks.

Core Features & Use Cases

  • Pre-clone Security Scanning: Inspects repositories for malicious hooks, poisoned MCP configurations, and credential-harvesting patterns.
  • Attack Pattern Detection: Scans for git hooks, CLAUDE.md files, MCP server configurations, and dependency trees for known malicious patterns.
  • Real-time Analysis: Blocks or warns about critical threats, providing actionable reports and allowing developers to review warnings.
  • Integration with Claude Code: Coordinates with mac-sentinel for runtime protection, maintaining repository reputation and enforcing scanning policies.

Quick Start

Run guard scan /path/to/repo to perform a security scan on a repository.

Frequently Asked Questions about repo-guardian

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scan a git repository for security threats before cloning?

Run `guard scan /path/to/repo` to perform a pre-clone security scan on a git repository. This identifies malicious hooks, poisoned MCP configurations, and credential-harvesting patterns before processing files.

What types of repository security risks can be detected in git hooks and configurations?

Repository security scanning detects malicious git hooks, poisoned MCP server configurations, credential-harvesting patterns, and suspicious dependencies by analyzing known attack patterns within repository files and configurations.

Does this repository security scanner work without installing any external dependencies?

Yes, this repository security scanner operates with no external dependencies. It requires only a Claude Code environment to analyze git hooks, configurations, and dependency trees for potential threats.

Can I scan a repository for malicious CLAUDE.md files and MCP server configurations?

Yes, you can scan for malicious CLAUDE.md files and MCP server configurations. The scanner analyzes these files alongside git hooks and dependency trees to identify known malicious patterns.

What is the best way to block malicious git hooks before processing repository files?

The best way to block malicious git hooks is running a pre-clone security scan that provides real-time analysis. It blocks or warns about critical threats and generates actionable reports for developer review.

When should I run a pre-clone repository security scan during development?

Run a pre-clone security scan before Claude Code processes any repository files. This mitigates risks from repository-borne attacks by identifying malicious hooks, configurations, and dependencies early.