security-scan

Audit Claude Code configurations for security vulnerabilities and misconfigurations.

16|3|Updated Mar 12, 2026

Search Tags:#security #vulnerability #hooks #mcp #claude-code #scan #agentshield

Ready to run

npx skills add https://github.com/sehoon787/my-claude --skill security-scan-sehoon787

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/sehoon787/my-claude/tree/main/skills/ecc/security-scan
Command: npx skills add https://github.com/sehoon787/my-claude --skill security-scan-sehoon787

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audit Claude Code configurations for security vulnerabilities, misconfigurations, and potential prompt injections using AgentShield.

Core Features & Use Cases

Scans CLAUDE.md for hardcoded secrets, auto-run instructions, and prompt injection patterns
Validates critical files like settings.json and mcp.json, hooks, and agent definitions for risky configurations
Provides prioritized remediation guidance to harden Claude Code deployments and prevent data leakage
Use Case: perform a security hygiene check after onboarding or major config changes.

Quick Start

Run a security scan against your .claude directory to identify issues and recommended fixes.

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, this Skill runs AgentShield against your target directory to audit CLAUDE.md, settings.json, MCP servers, and hook definitions for risky settings and prompt injection patterns.

What security issues can be detected in CLAUDE.md and MCP server configs?▼

Security scanning of CLAUDE.md and MCP server configs detects hardcoded secrets, auto-run instructions, prompt injection patterns, and risky hook or agent definitions that could lead to data leakage in your Claude Code deployment.

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

Yes, you need AgentShield installed to audit Claude Code settings, as the scan executes via npx ecc-agentshield scan against the target directory to validate configurations and generate remediation guidance.

How do I check Claude Code hooks and settings.json for misconfigurations?▼

To check Claude Code hooks and settings.json for misconfigurations, run an automated security scan that validates critical files against risky configuration patterns and provides prioritized remediation steps to harden your setup.

When should I run a security audit on my Claude Code deployment?▼

You should run a security audit on your Claude Code deployment after onboarding new projects or following major config changes to perform a security hygiene check and prevent potential data leakage from misconfigurations.