skills.rest
theandyalvarez7-ruby
theandyalvarez7-rubyCOMMUNITY
Explore all skills by this author →
GitHub

skill-security-auditor

Audit AI agent skills for security risks and generate JSON reports.

Updated Mar 5, 2026
Search Tags:#security#python#audit#prompt-injection#code-safety#ai-skills#dependency-supply-chain
One-click install
npx skills add https://github.com/theandyalvarez7-ruby/claude-skills --skill skill-security-auditor-theandyalvarez7-ruby
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-security-auditor
Source: https://github.com/theandyalvarez7-ruby/claude-skills/tree/main/engineering/skill-security-auditor
Command: npx skills add https://github.com/theandyalvarez7-ruby/claude-skills --skill skill-security-auditor-theandyalvarez7-ruby

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Security audits are required before installing AI agent skills to prevent malicious code, prompt injection, and risk-laden dependencies.

Core Features & Use Cases

  • Scans skill code and SKILL.md for dangerous patterns like os.system, eval, and subprocess calls.
  • Detects prompt injection in SKILL.md and references for hidden instructions.
  • Checks dependency supply chain for typosquatting and unpinned versions.
  • Verifies filesystem access stays within skill boundaries and reports remediation guidance.

Quick Start

Audit a local skill directory to obtain a security verdict and remediation guidance.

Frequently Asked Questions about skill-security-auditor

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

FAQPage Schema
How do I audit AI agent skills for security risks before installation?▼

To audit AI agent skills for security risks, you can scan local folders or git repositories to check code, prompt-injection patterns, dependencies, and filesystem access. The audit outputs a PASS, WARN, or FAIL verdict with remediation guidance.

What is prompt injection detection in AI skill code?▼

Prompt injection detection in AI skill code involves scanning SKILL.md and references directories for hidden instructions. This mechanism identifies malicious prompt injections before skill installation.

How do I scan a local skill directory for dangerous Python code patterns?▼

Scanning a local skill directory for dangerous Python code patterns checks for risky calls like os.system, eval, and subprocess. The audit assesses SKILL.md, scripts, and references to generate a security verdict.

Does the security audit check dependency supply chains for typosquatting?▼

Yes, the security audit checks the dependency supply chain for typosquatting and unpinned versions. It verifies dependencies in AI agent skills are safe before producing a JSON report.

Can I verify filesystem access boundaries for AI agent skills?▼

You can verify filesystem access boundaries by auditing AI agent skills to ensure they stay within designated limits. The audit checks filesystem access across SKILL.md, scripts, and references, reporting violations.

Related Skills

Explore More Software Engineering Skills→
Science-DiscoveryScience-Discovery
71

skill-security-auditor

Audit AI Skill packages for security risks and output PASS/WARN/FAIL reports.

Official
Advanced
spideynolovespideynolove
2

skill-security-auditor

Analyze skill directories or repositories for security risks and output a PASS/WARN/FAIL verdict.

Community
Advanced
shaun0927shaun0927

secure-check

Detect vulnerabilities and secrets in codebases during CI/CD pipelines.

Community
Advanced
djankiesdjankies

reviewing-dependencies

Detect unused, outdated, and vulnerable dependencies in npm projects.

Community
Advanced