security-scan

原文涵盖的主题

• Security Scan Skill
• When to Activate
• What It Scans
• Prerequisites
• Usage
• Basic Scan
• Output Formats
• Auto-Fix

Audit your Claude Code configuration for security issues using AgentShield. Setting up a new Claude Code project After modifying .claude/settings.json, CLAUDE.md, or MCP configs Before committing configuration changes When onboarding to a new repository with existing Claude Code configs Periodic security hygiene checks | File | Checks | |------|--------| | CLAUDE.md | Hardcoded secrets, auto-run instructions, prompt injection patterns | | settings.json | Overly permissive allow lists, missing deny lists, dangerous bypass flags | | mcp.json | Risky MCP servers, hardcoded env secrets, npx supply chain risks | | hooks/ | Command injection via interpolation, data exfiltration, silent error suppression | | agents/.md | Unrestricted tool access, prompt injection surface, missing model specs | AgentShield must be installed. Check and install if needed: Run against the current project's .claude/ directory: Apply safe fixes automatically (only fixes marked as auto-fixable): This will: Replace hardcoded secrets with environment variable references Tighten wildcard permissions to scoped alternatives Never modify manual-only suggestions Run the adversarial three-agent pipeline for deeper analy

这里只展示节选，请以完整原文和当前要求为准。