skill-security-auditor

Analyze AI agent skill files for command injection, data exfiltration, and prompt injection.

Updated May 25, 2026

Search Tags:#security #audit #AI agent #vulnerability scan #skill security

Ready to run

npx skills add https://github.com/ngquaanghuy/Crypto --skill skill-security-auditor-ngquaanghuy

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: skill-security-auditor
Source: https://github.com/ngquaanghuy/Crypto/tree/main/.agents/skills/skill-security-auditor
Command: npx skills add https://github.com/ngquaanghuy/Crypto --skill skill-security-auditor-ngquaanghuy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, subprocess, re, json, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a comprehensive security audit for AI agent skills, identifying and addressing potential vulnerabilities before installation.

Core Features & Use Cases

Security Audit: Detects malicious code, data exfiltration, and prompt injection in skill files.
Pre-Installation Check: Ensures the safety of Claude Code plugins, OpenClaw skills, and Codex skills.
Use Case: Before installing a new skill, run the security auditor to check for any potential security risks.

Quick Start

Audit a skill directory with:

python3 scripts/skill_security_auditor.py /path/to/skill-name/

Frequently Asked Questions about skill-security-auditor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I scan AI agent skills for vulnerabilities before installation?▼

To scan AI agent skills for vulnerabilities before installation, run a static code analysis on the skill directory using the security auditor script to detect malicious code and unauthorized access.

What types of security threats does static code analysis detect in skill files?▼

Static code analysis detects security threats in skill files such as command injection, data exfiltration, unauthorized access, and prompt injection in Markdown files.

Can I use this security auditor to check Python and Bash scripts?▼

Yes, you can use this security auditor to check Python and Bash scripts in skill directories, performing pattern matching and threat intelligence to identify potential security risks.

How do I run a pre-installation security check on a skill directory?▼

To run a pre-installation security check on a skill directory, execute the Python security auditor script and pass the target skill directory path as the argument.

Does prompt injection detection work on Markdown files?▼

Yes, prompt injection detection works on Markdown files by performing static analysis to identify malicious prompts and data exfiltration attempts before skill installation.

What security tools do I need for pattern matching and threat intelligence?▼

You need Python with subprocess, re, and json dependencies to perform pattern matching and threat intelligence operations during the static code analysis of skill files.