skills.rest
beratcelik1
beratcelik1COMMUNITY
Explore all skills by this author →
Website𝕏@beratcelik0GitHub

security-scan

Scan Claude Code configuration files for security vulnerabilities and misconfigurations.

1|Updated Mar 5, 2026
Search Tags:#security#configuration#mcp#auto-fix#claude-code#ci#agentshield
One-click install
npx skills add https://github.com/beratcelik1/compound-claude --skill security-scan-beratcelik1
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/beratcelik1/compound-claude/tree/main/skills/security-scan
Command: npx skills add https://github.com/beratcelik1/compound-claude --skill security-scan-beratcelik1

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Detect security vulnerabilities, misconfigurations, and prompt-injection risks in Claude Code repository configuration so teams can prevent credential leaks, dangerous MCP/server settings, and hook-based command injection before they reach production.

Core Features & Use Cases

  • Configuration-wide scanning: Inspects CLAUDE.md, .claude/settings.json, mcp.json, hooks/, and agent definitions for secrets, permissive allow-lists, and injection patterns.
  • Multiple output formats & CI integration: Produces terminal, JSON, Markdown, or HTML reports and can fail CI on high-severity findings.
  • Safe auto-fix and adversarial analysis: Applies auto-fixes for safe, clearly-marked changes and can run an Opus three-agent attacker/defender/auditor pipeline for deeper review.
  • Use Case: Run this Skill in pre-commit or CI to block commits that introduce hardcoded secrets, unrestricted shell access, or hook-based command injection.

Quick Start

Run AgentShield to scan the repository's .claude configuration and output a JSON report.

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 and prompt-injection risks?▼

Yes, you can integrate this configuration scanner into pre-commit hooks or CI pipelines to block commits that introduce hardcoded secrets, unrestricted shell access, or hook-based command injection. It fails CI automatically when high-severity findings are detected.

Can I automatically fix security misconfigurations in Claude Code settings and hooks?▼

When you provide an ANTHROPIC_API_KEY, the scanner supports an Opus three-agent adversarial analysis pipeline using attacker, defender, and auditor roles. This provides a deeper security review of your Claude Code configurations beyond standard static scanning.

What types of security risks can be detected in MCP server configurations and agent definitions?▼

The scanner detects credential leaks, dangerous MCP server settings, permissive allow-lists, and prompt-injection patterns in agent definitions. It inspects mcp.json and hook artifacts to prevent hook-based command injection before deployment.

Does the Claude Code security scanner work without external dependencies or API keys?▼

The scanner works without external dependencies to perform standard configuration scanning and generate reports. An ANTHROPIC_API_KEY is only required optionally to enable the Opus three-agent adversarial analysis pipeline for deeper security review.

Related Skills

Explore More Software Engineering Skills→
cescraflicescrafli

security-scan

Scan .claude directory configurations for security vulnerabilities and misconfigurations.

Community
Intermediate
Fl2vioFl2vio
1

Verification & Quality Assurance

Automate code, agent, and task verification with real-time truth scoring.

Community
Advanced
itallstartedwithaideaitallstartedwithaidea
31

secret-protection

Scan .env files, code, and diffs for exposed secrets and redact runtime outputs.

Community
Advanced
RangeyRoverRangeyRover
3

speckit.checker

Run static analysis across multiple languages and generate prioritized issue reports.

Community
Intermediate