Security Scan Skill Audit your Claude Code configuration for security issues using AgentShield. When to Activate - Setting up a new Claude Code project - After modifying , , or MCP configs - Before committing configuration changes - When onboarding to a new repository with existing Claude Code configs - Periodic security hygiene checks What It Scans | File | Checks | |------|--------| | | Hardcoded secrets, auto-run instructions, prompt injection patterns | | | Overly permissive allow lists, missing deny lists, dangerous bypass flags | | | Risky MCP servers, hardcoded env secrets, npx supply…