skills.rest
ZESCODE
ZESCODECOMMUNITY
Explore all skills by this author →
GitHub

security-scan

Scan Claude Code configuration files for secrets and misconfigurations.

Updated Jul 8, 2026
Search Tags:#security#vulnerability#audit#mcp#claude-code#hardening
One-click install
npx skills add https://github.com/ZESCODE/Zes-Orchestration-System --skill security-scan-zescode
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/ZESCODE/Zes-Orchestration-System/tree/main/.agents/skills/security-scan
Command: npx skills add https://github.com/ZESCODE/Zes-Orchestration-System --skill security-scan-zescode

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ecc-agentshield.

What problem does it solve?

This Skill identifies security vulnerabilities, misconfigurations, and potential prompt injection vectors within your Claude Code project environment to prevent unauthorized access or data leaks.

Core Features & Use Cases

  • Configuration Auditing: Scans CLAUDE.md, settings.json, and MCP configurations for hardcoded secrets and overly permissive access.
  • Risk Assessment: Grades your project security from A to F based on detected vulnerabilities and provides actionable remediation steps.
  • Use Case: Before deploying a new AI-assisted coding project, run this scan to ensure your MCP servers are isolated and no sensitive environment variables are exposed in your configuration files.

Quick Start

Use the security-scan skill to audit the current directory for vulnerabilities and generate a comprehensive security report.

Frequently Asked Questions about security-scan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I audit Claude Code configurations for security vulnerabilities?▼

Scanning Claude Code configs for security risks involves checking settings.json and MCP definitions for hardcoded secrets and permissive bash access. This process identifies misconfigurations and grades project hardening from A to F with actionable steps.

What is prompt injection detection in AI coding project files?▼

Prompt injection detection in AI coding project files identifies malicious patterns within CLAUDE.md and MCP configurations. It prevents unauthorized access by scanning for injection vectors that could compromise the Claude Code environment.

Do I need AgentShield to scan MCP servers for hardcoded secrets?▼

Yes, the AgentShield dependency is required to scan MCP servers for hardcoded secrets. It performs the static analysis required to detect exposed environment variables and generate security grades for project hardening.

How do I check MCP definitions for overly permissive bash access?▼

Checking MCP definitions for overly permissive bash access requires running a static analysis scan on your Claude Code project environment. This identifies misconfigurations in settings.json and grades your project security from A to F with remediation steps.

When should I run a security audit on my AI-assisted coding project?▼

Run a security audit on your AI-assisted coding project before deployment. Scanning configurations ensures MCP servers are isolated and verifies that no sensitive environment variables are exposed in your settings.json files.

Related Skills

Explore More Software Engineering Skills→
aayushsoamaayushsoam
1

security-scan

Scan Claude Code configurations for security vulnerabilities and generate severity-graded risk reports.

Community
Intermediate
oguzhanguvenkayaoguzhanguvenkaya

security-scan

Scan Claude Code configurations for security vulnerabilities and misconfigurations.

Community
Intermediate
Manvendra08Manvendra08
1

security-scan

Scan Claude Code configuration files for security vulnerabilities and misconfigurations.

Community
Intermediate
luongldptitluongldptit

security-scan

Scans Claude Code configs for vulnerabilities and outputs severity-graded reports.

Community
Intermediate