security-scan

Scan Claude Code configuration files for security vulnerabilities using AgentShield.

Updated Mar 16, 2026
One-click install
npx skills add https://github.com/thmspi/claude-setup --skill security-scan-thmspi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/thmspi/claude-setup/tree/main/.claude/skills/security-scan
Command: npx skills add https://github.com/thmspi/claude-setup --skill security-scan-thmspi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.

Core Features & Use Cases

  • Detects hardening gaps in CLAUDE.md, settings.json, MCP configs, hooks, and agent definitions.
  • Provides actionable remediation guidance and safe auto-fixes where possible.
  • Ideal for onboarding new repositories, post-change validations, and periodic security hygiene.

Quick Start

Run a quick security scan on the current repository's .claude directory using AgentShield.

Frequently Asked Questions about security-scan

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

FAQPage Schema
How do I scan Claude Code configurations for security vulnerabilities?

To scan Claude Code configurations for security vulnerabilities, run a security scan on your .claude directory. The tool analyzes CLAUDE.md, settings.json, MCP configs, hooks, and agent definitions to detect injection risks and misconfigurations.

When do I need to run a security scan on my CLAUDE.md and MCP configs?

You need to run a security scan on CLAUDE.md and MCP configs when setting up a new Claude Code project, after modifying configuration files, or during periodic security hygiene checks across your repositories.

Can I automatically fix misconfigurations and hardening gaps in Claude Code settings?

Yes, you can automatically fix misconfigurations and hardening gaps in Claude Code settings. The scan provides actionable remediation guidance and includes an optional auto-fix pass to safely correct detected vulnerabilities.

What formats can I export Claude Code security scan reports to?

You can export Claude Code security scan reports to multiple formats. The scanner produces reports in terminal output, JSON, Markdown, and HTML formats to integrate with various review workflows.

Does the security scan check MCP servers and hooks for injection risks?

Yes, the security scan checks MCP servers and hooks for injection risks. It uses AgentShield to analyze MCP configurations and hook definitions alongside CLAUDE.md to identify potential vulnerabilities.