security-scan

Scan Claude Code configurations for security vulnerabilities and misconfigurations.

Updated Mar 9, 2026
One-click install
npx skills add https://github.com/drxaibi/vibe-setup --skill security-scan-drxaibi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/drxaibi/vibe-setup/tree/main/.github/skills/security-scan
Command: npx skills add https://github.com/drxaibi/vibe-setup --skill security-scan-drxaibi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill safeguards your Claude Code configurations by proactively identifying and mitigating security vulnerabilities, misconfigurations, and potential injection risks within your project's setup.

Core Features & Use Cases

  • Comprehensive Auditing: Scans critical configuration files (.claude/settings.json, CLAUDE.md, MCP configs) and code structures (hooks/, agents/) for security flaws.
  • Vulnerability Detection: Identifies issues like hardcoded secrets, prompt injection vectors, command injection, and overly permissive access controls.
  • Use Case: Before deploying a new Claude Code project or after making significant configuration changes, run this scan to ensure your setup adheres to security best practices and is protected against common attack vectors.

Quick Start

Run a security scan on your current project's Claude Code configuration.

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, you can use a tool that analyzes files like CLAUDE.md, settings.json, and MCP servers. It detects hardcoded secrets, prompt injection, and command injection risks by executing the ecc-agentshield package via npx.

What security risks should I look for in my Claude Code setup?

Security risks in a Claude Code setup include hardcoded secrets, prompt injection vectors, command injection, and overly permissive access controls. Scanning your configuration files and code structures like hooks and agents identifies these vulnerabilities.

Can I audit MCP servers and hooks for prompt injection risks?

Yes, you can audit MCP servers and hooks for prompt injection risks by running a comprehensive security scan. This process analyzes your configuration files and code structures to identify potential injection vectors and misconfigurations.

Does the security scan require npx and the ecc-agentshield package to run?

Yes, the security scan requires npx to execute the ecc-agentshield package. This setup allows the tool to analyze your project's Claude Code configuration for misconfigurations and security flaws.

When should I run a security scan on my Claude Code project?

You should run a security scan on your Claude Code project before deploying a new setup or after making significant configuration changes. This ensures your setup adheres to security best practices and is protected against common attack vectors.