Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Scans a repository's agent configuration files for known malicious patterns before you trust or run its configurations. Checks Claude settings, skill files, MCP configs, and project instruction files. Outputs a severity-grouped report with recommendations.
Catches agent-level attack vectors like hook auto-approval, hidden curl|bash chains, and instruction injection that standard code review tools don't check for.
When to use it
- Auditing a cloned open-source repo before running its agent setup
- Reviewing a contractor's codebase for injected agent instructions
- Checking for malicious hooks after a pull request modifies .claude/
- Security review before onboarding a new project with MCP integrations
- Catching prompt injection attempts hidden in CLAUDE.md files
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: scan this repo for malicious agent configs before I start working in it
- 1Resolves SKILL_DIR and PROJECT_ROOT paths
- 2Runs vet_repo.py against the project root
- 3Scans .claude/settings.json for dangerous hook configs
- 4Scans .claude/skills/, .mcp.json, and CLAUDE.md for injection patterns
- 5Groups findings by severity and generates recommendations
Structured report listing CRITICAL/HIGH/MEDIUM/LOW/INFO findings across all agent config files, with actionable remediation steps for each issue