skills.rest
freedom909
freedom909COMMUNITY
Explore all skills by this author →
GitHub

security-scan

Scan Claude Code configuration files for security vulnerabilities and misconfigurations using AgentShield.

Updated Mar 18, 2026
Search Tags:#claude code#MCP servers#security scan#prompt injection#configuration audit#agentshield#ci security
One-click install
npx skills add https://github.com/freedom909/real-estate-saas --skill security-scan-freedom909
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/freedom909/real-estate-saas/tree/main/.trae/skills/security-scan
Command: npx skills add https://github.com/freedom909/real-estate-saas --skill security-scan-freedom909

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ecc-agentshield.

What problem does it solve? Claude Code configuration files like CLAUDE.md, settings.json, and MCP server configs can contain hardcoded secrets, overly permissive permissions, and prompt injection risks that are easy to overlook during manual review. ## Core Features & Use Cases - Configuration Auditing: Scans CLAUDE.md, settings.json, mcp.json, hooks, and agent definitions for hardcoded secrets, dangerous permissions, and injection patterns. - Auto-Fix and Reporting: Applies safe automatic fixes and outputs reports in terminal, JSON, Markdown, or HTML formats with severity grades from A to F. - Use Case: Before committing changes to your .claude/ directory, run a scan to catch a wildcard Bash(*) permission or a hardcoded API key, then apply automatic fixes and integrate the GitHub Action into CI to block insecure configs. ## Quick Start Ask the AI to scan the current project's Claude Code configuration for security issues and report any critical or high severity findings.

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 issues?▼

Run npx ecc-agentshield scan in your project directory to audit the .claude/ folder. It checks CLAUDE.md, settings.json, mcp.json, hooks, and agent files, then reports findings with severity grades from A to F.

What security risks does AgentShield detect in settings.json?▼

AgentShield detects overly permissive allow lists like Bash(*), missing deny lists, and dangerous bypass flags in settings.json. It also flags hardcoded API keys and tokens in any configuration file as critical findings.

Can AgentShield automatically fix security findings?▼

Yes, running npx ecc-agentshield scan --fix applies safe automatic fixes such as replacing hardcoded secrets with environment variable references and tightening wildcard permissions. Suggestions marked manual-only are never modified.

Does the security scan work in CI/CD pipelines?▼

Yes, use the JSON output format for CI integration or add the affaan-m/agentshield GitHub Action to your workflow. You can set a minimum severity threshold and configure it to fail the build when findings are detected.

What are the limitations of the automatic security scan?▼

The standard scan uses static pattern checks and may miss novel attack vectors. The optional Opus deep analysis mode provides adversarial red-team review but requires an ANTHROPIC_API_KEY and additional setup.

Related Skills

Explore More Software Engineering Skills→
sakamoto-family-smilesakamoto-family-smile

security-scan

Audit Claude Code configuration files for security vulnerabilities and misconfigurations.

Community
Advanced
0xHoneyJar0xHoneyJar

audit-env

Scan environment files, client code, and git history for secret leakage.

Official
Advanced
JoaoPedroAmaralJoaoPedroAmaral

vulnerability-scanner

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

Community
Advanced
voidrotvoidrot

security-scan

Scan Claude Code and agent configurations for security vulnerabilities.

Community
Advanced