skills.rest
danielkhigay
danielkhigayCOMMUNITY
Explore all skills by this author →
GitHub

security-scan

Scan Claude Code configurations for security vulnerabilities and misconfigurations.

Updated Feb 19, 2026
Search Tags:#security#audit#claude#configuration#mcp#agentshield
One-click install
npx skills add https://github.com/danielkhigay/gaz --skill security-scan-danielkhigay
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/danielkhigay/gaz/tree/main/.claude/skills/security-scan
Command: npx skills add https://github.com/danielkhigay/gaz --skill security-scan-danielkhigay

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Identify security vulnerabilities, misconfigurations, and injection risks in Claude Code configurations to reduce exposure and strengthen deployment hygiene.

Core Features & Use Cases

  • Audits CLAUDE.md for secrets and prompt injection patterns
  • Validates settings.json, mcp.json, hooks, and agent definitions for risky configurations
  • Provides remediation guidance and safe defaults to harden deployments

Quick Start

Run the AgentShield scan on your .claude directory to surface security issues.

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?▼

Scan Claude Code configurations by running an AgentShield audit across CLAUDE.md, settings.json, mcp.json, hooks, and agent definitions to detect secrets exposure and prompt injection risks. This surfaces security vulnerabilities and provides remediation guidance to harden deployments.

What security issues should I look for in MCP server configurations and hooks?▼

Security audits of MCP server configurations and hooks detect risky MCP servers, exposed secrets, and injection risks. Validating these files ensures risky configurations are identified and replaced with safe defaults to strengthen deployment hygiene.

Can I audit CLAUDE.md files for exposed secrets and prompt injection patterns?▼

Yes, auditing CLAUDE.md files identifies embedded secrets and prompt injection patterns. The scan evaluates configuration contents to reduce exposure and applies checks to surface misconfigurations that could compromise Claude Code deployments.

Does AgentShield work with settings.json and mcp.json to detect risky configurations?▼

AgentShield validates settings.json and mcp.json to detect risky configurations and risky MCP servers. It applies security checks to these configuration files to identify misconfigurations and provide remediation guidance for hardening your setup.

What is the best way to harden Claude Code deployments and fix configuration misconfigurations?▼

Harden Claude Code deployments by running a security scan that provides remediation guidance and safe defaults. Auditing configuration files like CLAUDE.md and mcp.json detects vulnerabilities and applies corrections to strengthen overall deployment hygiene.

When should I run a security audit on my .claude directory configurations?▼

Run a security audit on your .claude directory whenever modifying CLAUDE.md, settings.json, hooks, or agent definitions. Scanning detects secrets exposure and injection risks early, providing remediation guidance to maintain secure deployment hygiene.

Related Skills

Explore More Software Engineering Skills→
bitwardenbitwarden
129

reviewing-claude-config

Review Claude Code configuration files for security risks and quality issues.

Official
Basic
ValenBorrasValenBorras
1

security-scan

Scan Claude Code configurations for security vulnerabilities and misconfigurations.

Community
Advanced
gganbukim1gganbukim1

security-scan

Scan Claude Code configuration files for security vulnerabilities and injection risks.

Community
Advanced
Michae2xlMichae2xl

security-scan

Scan Claude Code configurations for security vulnerabilities using AgentShield.

Community
Advanced