skills.rest
Tonybleything76
Tonybleything76COMMUNITY
Explore all skills by this author →
GitHub

skill-security-auditor

Scan AI agent skills for security vulnerabilities and malicious code.

Updated Mar 4, 2026
Search Tags:#security#vulnerability#audit#prompt injection#malware#code scanning
One-click install
npx skills add https://github.com/Tonybleything76/more-claude-skills --skill skill-security-auditor-tonybleything76
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-security-auditor
Source: https://github.com/Tonybleything76/more-claude-skills/tree/main/engineering/skill-security-auditor
Command: npx skills add https://github.com/Tonybleything76/more-claude-skills --skill skill-security-auditor-tonybleything76

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill acts as a crucial security gate, scanning AI agent skills for potential vulnerabilities and malicious code before they are installed, protecting users from security threats.

Core Features & Use Cases

  • Code Scanning: Analyzes Python, Bash, and JavaScript scripts for dangerous patterns like command injection, code execution, and network exfiltration.
  • Prompt Injection Detection: Scans SKILL.md and reference files for attempts to override instructions, bypass safety features, or exfiltrate data.
  • Dependency Analysis: Checks for typosquatting in dependencies and flags runtime installations.
  • File System Auditing: Identifies boundary violations, hidden files, and suspicious binaries.
  • Use Case: Before installing a new skill from an unknown source, run this auditor to get a PASS/WARN/FAIL verdict and detailed findings, ensuring a safe environment.

Quick Start

Use the skill-security-auditor skill to audit the local directory '/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 security vulnerabilities and malicious code?▼

To scan AI agent skills for security vulnerabilities, run the auditor against the local skill directory to analyze Python, Bash, and JavaScript scripts for command injection, code execution, and network exfiltration risks.

Can I detect prompt injection in SKILL.md and reference files before installing a skill?▼

Yes, you can detect prompt injection in SKILL.md and reference files by scanning for attempts to override instructions, bypass safety features, or exfiltrate data, resulting in a detailed PASS/WARN/FAIL verdict with remediation guidance.

Does the security audit check for dependency supply chain risks and typosquatting?▼

The security audit does check for dependency supply chain risks by scanning for typosquatting in dependencies and flagging runtime installations, helping identify malicious packages before skill installation.

What is the best way to audit file system access for hidden files and boundary violations in agent skills?▼

The best way to audit file system access for hidden files and boundary violations is to run a security scan that identifies suspicious binaries and unauthorized directory boundaries, yielding a PASS/WARN/FAIL verdict.

How does the security auditor handle code execution and network exfiltration risks in scripts?▼

The security auditor handles code execution and network exfiltration risks by analyzing dangerous patterns in Python, Bash, and JavaScript scripts, providing a PASS/WARN/FAIL verdict with specific remediation steps to ensure a safe environment.

What are the limitations when auditing skills for command injection and malicious code?▼

Limitations when auditing skills for command injection include relying on pattern analysis for Python, Bash, and JavaScript scripts, which may not catch zero-day vulnerabilities or obfuscated malicious code outside the scanned directory.

Related Skills

Explore More Software Engineering Skills→
Serverless-DevsServerless-Devs
20

ar-skill

Upload, list, get, download, and delete Skill packages on the platform.

Official
Advanced
tapanshahtapanshah

skill-security-auditor

Scan AI agent skills for security vulnerabilities and malicious code.

Community
Advanced
AscendAscend
31

skill-auditor

Audit AI agent skills and prompts for safety before deployment.

Official
Advanced
amanhsnamanhsn

skill-security-auditor

Audit AI agent skills for security vulnerabilities using static analysis.

Community
Advanced