skills.rest
AgLyx3
AgLyx3COMMUNITY
Explore all skills by this author →
GitHub

skill-security-auditor

Audit AI agent skills for security risks and generate a verdict report.

Updated Mar 21, 2026
Search Tags:#security#security-audit#code-scan#prompt-injection#ai-skill#risk-report
One-click install
npx skills add https://github.com/AgLyx3/My-Note-App-Not-Just-a-Note-App --skill skill-security-auditor-aglyx3
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-security-auditor
Source: https://github.com/AgLyx3/My-Note-App-Not-Just-a-Note-App/tree/main/.cursor/skills/engineering/skill-security-auditor
Command: npx skills add https://github.com/AgLyx3/My-Note-App-Not-Just-a-Note-App --skill skill-security-auditor-aglyx3

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Security audit and vulnerability scanner for AI agent skills before installation, helping teams evaluate untrusted skills and reduce risk before enabling them in production contexts.

Core Features & Use Cases

  • Produces a clear PASS / WARN / FAIL verdict with findings and remediation guidance for AI agent skills.
  • Scans code for dangerous patterns (Python/Bash/JS), prompts for SKILL.md in-line review, dependency supply chain, and file system boundaries.
  • Useful in pre-install gates, CI/CD checks, and manual reviews of skills from untrusted sources.

Quick Start

Run the auditor on a local skill directory to generate a structured security report before installation.

Frequently Asked Questions about skill-security-auditor

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

FAQPage Schema
How do I run a security audit on an AI agent skill before installation?▼

To run a security audit on an AI agent skill, execute the auditor on a local skill directory or git repository to generate a structured JSON report containing PASS, WARN, or FAIL verdicts with specific remediation guidance.

What is a prompt injection detection check for untrusted AI skills?▼

Prompt injection detection for untrusted AI skills involves scanning the SKILL.md file for in-line malicious prompts to ensure the skill's instructions do not manipulate the agent's behavior or override system boundaries.

Can I use this security auditor to scan code execution patterns in Python and Bash?▼

Yes, you can use this security auditor to scan code execution patterns in Python, Bash, and JavaScript files, identifying dangerous commands and enforcing file system boundaries before integrating the skill.

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

Yes, the skill security audit checks for dependency supply chain risks by evaluating external packages and dependencies referenced in the skill directory to prevent the introduction of vulnerable or compromised libraries.

What is the best way to integrate a pre-install security gate into CI/CD for AI agent skills?▼

The best way to integrate a pre-install security gate into CI/CD for AI agent skills is to run the auditor automatically against skill repositories, failing the pipeline if the structured JSON report outputs a WARN or FAIL verdict.

When do I need a structured JSON report for AI skill vulnerability scanning?▼

You need a structured JSON report for AI skill vulnerability scanning when performing automated pre-install gates or manual reviews, allowing systems to programmatically parse security findings, file system boundary violations, and remediation steps.

Related Skills

Explore More Software Engineering Skills→
devCharuzudevCharuzu

skill-security-auditor

Scan AI agent skill code, prompts, and dependencies for security risks.

Community
Advanced
lagarcesslagarcess
1

skill-security-auditor

Scan AI agent skill directories for security vulnerabilities and malicious patterns.

Community
Advanced
jassicsjassics
6

secure-pipeline

Review and secure CI/CD pipelines with automated security scanning gates.

Community
Advanced
tapanshahtapanshah

skill-security-auditor

Scan AI agent skills for security vulnerabilities and malicious code.

Community
Advanced