security-scan

Scan Claude Code configurations for vulnerabilities and misconfigurations.

Updated Nov 19, 2025
One-click install
npx skills add https://github.com/Sake-Team/SmartSake --skill security-scan-sake-team
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/Sake-Team/SmartSake/tree/main/backup/skills/security-scan
Command: npx skills add https://github.com/Sake-Team/SmartSake --skill security-scan-sake-team

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ecc-agentshield, and includes scripts (resource) components.

What problem does it solve?

This Skill provides automated security scanning for Claude Code configurations, identifying vulnerabilities and misconfigurations.

Core Features & Use Cases

  • Security Vulnerability Scan: Detects hardcoded secrets, auto-run instructions, and prompt injection patterns.
  • Configuration Analysis: Reviews CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
  • Use Case: Use this Skill to regularly audit your Claude Code configuration to ensure it's secure before deployment or significant changes.

Quick Start

Run a security scan on your Claude Code configuration by executing '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 for security vulnerabilities?

Scanning Claude Code configuration for security vulnerabilities is done by executing 'npx ecc-agentshield scan' to automatically detect hardcoded secrets, auto-run instructions, and prompt injection patterns in your .claude/ directory.

What is security scanning for Claude Code and what does it check?

Security scanning for Claude Code is an automated audit of your configuration files that checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions to identify misconfigurations and vulnerabilities.

Does the security scan require AgentShield to run?

Yes, the security scan requires the AgentShield dependency to operate, as it uses the ecc-agentshield module to analyze your Claude Code configuration files and identify potential security risks.

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

You should run a security scan on your Claude Code configuration before deployment or significant changes to ensure your settings, hooks, and agent definitions are free from vulnerabilities and hardcoded secrets.

What is the best way to detect prompt injection patterns in Claude Code settings?

The best way to detect prompt injection patterns in Claude Code settings is to use an automated configuration auditing tool like AgentShield to scan your .claude/ directory for malicious instructions.

Why does my Claude Code security scan report auto-run instructions as a risk?

A Claude Code security scan reports auto-run instructions as a risk because they can execute commands without user consent, creating a vulnerability if injected or misconfigured in your settings.