skills.rest
agentmatters
agentmattersOFFICIAL
Explore all skills by this author →
WebsiteGitHub

security-scan

Audit Claude Code configurations for security vulnerabilities and injection risks.

3|2|Updated Mar 8, 2026
Search Tags:#security#configuration#mcp#vulnerabilities#claude-code#scan#agentshield
One-click install
npx skills add https://github.com/agentmatters/mullai-bot --skill security-scan-agentmatters
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/agentmatters/mullai-bot/tree/main/src/Mullai.Skills/Skills/claude-code-everything/security-scan
Command: npx skills add https://github.com/agentmatters/mullai-bot --skill security-scan-agentmatters

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Claude Code configurations often contain sensitive information and misconfigurations that expose systems to risk. This skill scans those configurations to detect vulnerabilities and injection risks, helping teams harden their Claude Code setup.

Core Features & Use Cases

  • Security audits of CLAUDE.md for hardcoded secrets, auto-run instructions, and prompt injection patterns.
  • Configuration checks for settings.json and mcp.json to identify overly permissive permissions, missing deny lists, and risky bypass flags.
  • Hook and agent review for hooks/ and agents/*.md to uncover potential data exfiltration, surface risks, and missing model specs.
  • Onboarding and periodic hygiene: use during project setup and recurring security reviews to maintain secure Claude Code configurations.

Quick Start

Run a secure scan of your Claude Code configuration in the project 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 and injection risks?▼

Audit Claude Code configurations for security vulnerabilities by running AgentShield to scan CLAUDE.md, settings.json, mcp.json, hooks, and agents/*.md for misconfigurations, hardcoded secrets, and injection risks.

What security risks should I check for in MCP configs and agent definitions?▼

Security scans of MCP configs and agent definitions detect overly permissive permissions, missing deny lists, risky bypass flags, potential data exfiltration, surface risks, and missing model specs.

Do I need AgentShield installed to perform a Claude Code security audit?▼

Yes, AgentShield must be installed to perform a Claude Code security audit, as the skill relies on it to detect vulnerabilities, misconfigurations, and injection risks across project files.

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

Run a security scan during project onboarding and setup, as well as periodically for recurring hygiene checks, to maintain secure Claude Code configurations and detect emerging injection risks.

Does the security scan check CLAUDE.md for hardcoded secrets and auto-run instructions?▼

Yes, the security scan audits CLAUDE.md to identify hardcoded secrets, auto-run instructions, and prompt injection patterns that could expose your system to risk.

Related Skills

Explore More Software Engineering Skills→
nahisahonahisaho
12

security-auditor

Audit code, configurations, and dependencies for security vulnerabilities.

Community
Advanced
KuaaMUKuaaMU
4

security-scan

Scan Claude Code configurations for security vulnerabilities and misconfigurations.

Community
Intermediate
kk20300113-pngkk20300113-png

security-scan

Scan Claude Code configuration files for security vulnerabilities and misconfigurations.

Community
Intermediate
pr-pmpr-pm
121

claude-hook-writer

Review Claude Code hooks for security vulnerabilities and reliability issues.

Community
Intermediate