skills.rest
cescrafli
cescrafliCOMMUNITY
Explore all skills by this author →
GitHub

security-scan

Scan .claude directory configurations for security vulnerabilities and misconfigurations.

Updated Mar 26, 2026
Search Tags:#security#hooks#mcp#claude-code#scan#agentshield
One-click install
npx skills add https://github.com/cescrafli/compyrasion --skill security-scan-cescrafli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/cescrafli/compyrasion/tree/main/skills/security-scan
Command: npx skills add https://github.com/cescrafli/compyrasion --skill security-scan-cescrafli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audit Claude Code configurations for security issues, misconfigurations, and potential prompt-injection risks to prevent breaches.

Core Features & Use Cases

  • Checks CLAUDE.md for hardcoded secrets and prompt-injection patterns
  • Validates settings.json and MCP configs for risky permissions and bypass flags
  • Scans mcp.json, hooks, and agent definitions to surface exposure risks
  • Works during project setup, post-change checks, and periodic security hygiene

Quick Start

Run an AgentShield scan against the repository's .claude directory to identify security risks.

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?▼

You can scan Claude Code configurations for vulnerabilities by running AgentShield against the .claude directory to detect hardcoded secrets, risky permissions, and prompt-injection patterns.

What files do I need to check for prompt-injection risks in Claude Code?▼

You check prompt-injection risks in Claude Code by scanning CLAUDE.md for malicious patterns, alongside mcp.json, hooks/, and agents/*.md files to surface exposure risks.

Do I need AgentShield to audit settings.json and mcp.json for risky permissions?▼

Yes, AgentShield installation is required to audit settings.json and mcp.json for risky permissions, bypass flags, and misconfigurations within the Claude Code environment.

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

Run a security scan on your Claude Code project during initial setup, after modifying CLAUDE.md or settings.json, and during periodic security hygiene checks.

What is the best way to prevent breaches from Claude Code misconfigurations?▼

Preventing breaches from Claude Code misconfigurations involves auditing the .claude directory to validate permissions, bypass flags, and hooks for potential exposure risks.

Related Skills

Explore More Software Engineering Skills→
vinwangvinwang

security-scan

Audit Claude Code configurations for security issues and misconfigurations.

Community
Advanced
oguzhanguvenkayaoguzhanguvenkaya

security-scan

Scan Claude Code configurations for security vulnerabilities and misconfigurations.

Community
Intermediate
adomotadomot

security-scan

Audit Claude Code configurations for security vulnerabilities and injection risks.

Community
Intermediate
SergeiGolosSergeiGolos
1

vulnerability-scanner

Detect and prioritize security vulnerabilities across dependencies, secrets, code patterns, and configurations.

Community
Advanced