skills.rest
multiplex-ai
multiplex-aiOFFICIAL
Explore all skills by this author →
Website𝕏@Muggle_AIGitHub

security-scan

Scan Claude Code configurations for security vulnerabilities and misconfigurations.

2|Updated Mar 20, 2026
Search Tags:#security#mcp#auditing#vulnerabilities#claude-code#misconfigurations#agentshield
One-click install
npx skills add https://github.com/multiplex-ai/muggle-ai-teams --skill security-scan-multiplex-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/multiplex-ai/muggle-ai-teams/tree/main/skills/security-scan
Command: npx skills add https://github.com/multiplex-ai/muggle-ai-teams --skill security-scan-multiplex-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Scan Claude Code configurations for security vulnerabilities, misconfigurations, and injection risks using AgentShield, catching issues before they lead to incidents.

Core Features & Use Cases

  • Audits CLAUDE.md for prompt injection patterns and hardcoded secrets
  • Validates settings.json and MCP configs for risky permissions and environment exposure
  • Generates actionable remediation guidance and supports automated safety checks

Quick Start

Run a security scan on your .claude workspace to identify vulnerabilities.

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, you can use AgentShield to audit CLAUDE.md, settings.json, MCP configs, and hooks for vulnerabilities, misconfigurations, and injection risks. The tool identifies security flaws and generates actionable remediation guidance.

What security risks should I look for in MCP configs and settings.json?▼

Common security risks in MCP configs and settings.json include risky permissions, environment variable exposure, and hardcoded secrets. AgentShield validates these configurations to catch misconfigurations and prompt injection patterns before they lead to incidents.

Does AgentShield work with CLAUDE.md files to detect prompt injection?▼

Yes, AgentShield audits CLAUDE.md files to detect prompt injection patterns and hardcoded secrets. It scans your .claude workspace to identify security vulnerabilities and generates actionable remediation guidance for proactive hardening.

Can I automatically fix misconfigurations found during a Claude Code security scan?▼

Yes, you can automatically fix misconfigurations because the security scan supports optional auto-fix features. AgentShield performs automated scans of your Claude Code configurations and provides remediation guidance to harden your setup.

What's the best way to audit agent definitions for security risks?▼

The best way to audit agent definitions for security risks is using AgentShield to scan your .claude workspace. It identifies vulnerabilities and injection risks across agent definitions, CLAUDE.md, and MCP configs, providing multiple output formats for remediation.

Why does my Claude Code configuration need proactive hardening?▼

Claude Code configuration needs proactive hardening to prevent security incidents caused by misconfigurations, risky permissions, and injection risks. AgentShield catches these issues in files like settings.json and MCP configs before they can be exploited.

Related Skills

Explore More Software Engineering Skills→
Clean1inesClean1ines

security-scan

Audit Claude Code configurations for security vulnerabilities with AgentShield.

Community
Advanced
Kling0012Kling0012
1

V3 Security Overhaul

Secure claude-flow v3 through threat modeling, CVE remediation, and security testing.

Community
Advanced
zero3041zero3041
1

security-scan

Scan Claude Code configurations for vulnerabilities, misconfigurations, and injection risks.

Community
Advanced
diegocconsolinidiegocconsolini
6

plugin-security-checker

Scan Claude Code plugins for security vulnerabilities and insecure patterns.

Community
Advanced