skills.rest
arbisoft
arbisoftOFFICIAL
Explore all skills by this author →
Website𝕏@arbisoftGitHub

security-scan

Audit Claude Code configurations for security vulnerabilities using AgentShield.

4|7|Updated Apr 9, 2026
Search Tags:#security#claude#config#vulnerabilities#scan#agentshield
One-click install
npx skills add https://github.com/arbisoft/ai-skillforge --skill security-scan-arbisoft
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: security-scan
Source: https://github.com/arbisoft/ai-skillforge/tree/main/Claude/skills/security-scan
Command: npx skills add https://github.com/arbisoft/ai-skillforge --skill security-scan-arbisoft

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill audits Claude Code configurations for security vulnerabilities, misconfigurations, and injection risks using AgentShield across the .claude/ directory, CLAUDE.md, settings.json, mcp.json, hooks, and agent definitions.

Core Features & Use Cases

  • Scans critical Claude Code files for secrets, permission issues, and risky MCP settings.
  • Detects prompt injection patterns, hardcoded tokens, and unsafe tool access.
  • Real-world use: before committing changes to a repository, run this scan to surface findings and harden the configuration.

Quick Start

Run an AgentShield scan on your project's Claude configuration to generate a security 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 my Claude Code configuration for security vulnerabilities?▼

To detect prompt injection risks in CLAUDE.md, run an AgentShield scan to analyze your configuration files for injection patterns, hardcoded tokens, and unsafe tool access permissions.

What is the best way to check MCP configs for hardcoded secrets before committing?▼

The best way to check MCP configs for hardcoded secrets is to run an automated security scan using AgentShield, which inspects mcp.json and related files to produce actionable security findings before you commit changes.

Does AgentShield work with Claude Code hooks and settings.json files?▼

Yes, AgentShield works with Claude Code by auditing settings.json, hooks, and agent definitions to identify permission misconfigurations and injection risks across your project setup.

Can I audit my .claude directory for unsafe tool access and permission issues?▼

You can audit your .claude directory for unsafe tool access by running a security scan that checks permission misconfigurations across CLAUDE.md, settings.json, mcp.json, and hooks to harden your repository.

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

You should run a security scan on your Claude Code configuration when setting up a new project, modifying CLAUDE.md or MCP configs, or performing ongoing repository hygiene to catch newly introduced injection risks.

Related Skills

Explore More Software Engineering Skills→
nahisahonahisaho
12

security-auditor

Audit code, configurations, and dependencies for security vulnerabilities.

Community
Advanced
luongldptitluongldptit

security-scan

Scans Claude Code configs for vulnerabilities and outputs severity-graded reports.

Community
Intermediate
zero3041zero3041
1

security-scan

Scan Claude Code configurations for vulnerabilities, misconfigurations, and injection risks.

Community
Advanced
ZESCODEZESCODE

security-scan

Scan Claude Code configuration files for secrets and misconfigurations.

Community
Advanced