security-scan

Scans Claude Code configuration files for security vulnerabilities using AgentShield.

5|Updated Feb 6, 2026

Search Tags:#security #vulnerability #claude code #configuration #scan #agent shield

Ready to run

npx skills add https://github.com/FaisalAlqarni/sp-ecc --skill security-scan-faisalalqarni

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill identifies and helps remediate security vulnerabilities within your Claude Code project's configuration files, preventing potential breaches and ensuring compliance.

Core Features & Use Cases

Vulnerability Detection: Scans CLAUDE.md, settings.json, mcp.json, hooks/, and agents/*.md for common security flaws.
Automated Remediation: Offers an --fix option to automatically correct issues like hardcoded secrets and overly permissive settings.
Use Case: Before committing a significant change to your project's security settings, run a security-scan to catch any accidental exposures.

Quick Start

Run a security scan on the current project using npx ecc-agentshield scan.

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 configuration files for security vulnerabilities?▼

To scan Claude Code configuration files for security vulnerabilities, run the command npx ecc-agentshield scan to analyze your project's settings, hooks, and agent definitions for hardcoded secrets and prompt injection patterns.

What security flaws can AgentShield detect in Claude Code projects?▼

AgentShield detects security flaws in Claude Code projects by scanning for hardcoded secrets, prompt injection patterns, and overly permissive access controls within configuration files like CLAUDE.md, settings.json, and mcp.json.

Can I automatically fix insecure settings and hardcoded secrets in Claude Code?▼

You can automatically fix insecure settings and hardcoded secrets in Claude Code by running the security scan with the --fix option, which automatically corrects overly permissive settings and accidental exposures.

Does the security scan check hooks and agents definitions for prompt injection?▼

The security scan does check hooks and agents definitions for prompt injection by scanning the hooks/ directory and agents/*.md files to identify prompt injection patterns and ensure secure development practices.

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

You should run a security scan on your Claude Code project configuration during project setup, after configuration modifications, and as a pre-commit check to catch accidental exposures before committing significant changes.