skills.rest
yd5768365-hue
yd5768365-hueCOMMUNITY
Explore all skills by this author →
GitHub

security-scan

Audit Claude Code configurations for security vulnerabilities and misconfigurations.

Updated Aug 27, 2026
Search Tags:#security#vulnerability#claude code#configuration#scan#agent shield
One-click install
npx skills add https://github.com/yd5768365-hue/caw-cli --skill security-scan-yd5768365-hue
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/yd5768365-hue/caw-cli/tree/main/everything-claude-code-main/everything-claude-code-main/docs/ja-JP/skills/security-scan
Command: npx skills add https://github.com/yd5768365-hue/caw-cli --skill security-scan-yd5768365-hue

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill proactively identifies and helps mitigate security vulnerabilities, misconfigurations, and injection risks within your Claude Code project settings, ensuring a more secure development environment.

Core Features & Use Cases

  • Comprehensive Auditing: Scans CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions for security flaws.
  • Vulnerability Detection: Identifies hardcoded secrets, prompt injection patterns, overly permissive settings, and supply chain risks.
  • Use Case: Before committing changes to your Claude Code project, run this security scan to catch any accidental exposure of API keys or introduction of dangerous commands, preventing potential breaches.

Quick Start

Run a security scan on the current project's .claude/ directory.

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, audit the `.claude/` directory using AgentShield to detect hardcoded secrets, prompt injection, and overly permissive settings in CLAUDE.md and settings.json.

What security risks exist in Claude Code MCP servers and hooks?▼

Security risks in Claude Code MCP servers and hooks include prompt injection patterns, hardcoded secrets, supply chain risks, and overly permissive settings that can be identified through a comprehensive configuration audit.

Do I need AgentShield installed to scan Claude Code settings?▼

Yes, you need AgentShield installed or executable via npx to scan Claude Code settings, as it provides the scanning and auto-fixing capabilities required to identify and mitigate security flaws.

Can I automatically fix security misconfigurations in Claude Code?▼

You can automatically fix security misconfigurations in Claude Code using AgentShield, which supports potential auto-fixing of identified security flaws like hardcoded secrets and injection risks found during the scan.

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

You should run a security scan on your Claude Code project before committing changes to catch accidental exposure of API keys or introduction of dangerous commands, preventing potential breaches in your development environment.

Related Skills

Explore More Software Engineering Skills→
drxaibidrxaibi

security-scan

Scan Claude Code configurations for security vulnerabilities and misconfigurations.

Community
Advanced
micaelmaltamicaelmalta
1

security-reviewer

Identify and remediate security vulnerabilities across code, configuration, and architecture.

Community
Advanced
KuaaMUKuaaMU
4

security-scan

Scan Claude Code configurations for security vulnerabilities and misconfigurations.

Community
Intermediate
woxiangyangzhimaowoxiangyangzhimao
3

security-scan

Scan Claude Code configurations for secrets and injection risks.

Community
Advanced