skill-security-audit

Audit SKILL.md files for malicious, misconfigured, or untrusted content.

Updated Jun 8, 2026
One-click install
npx skills add https://github.com/az9713/atlas-agent-tutorial --skill skill-security-audit-az9713
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-security-audit
Source: https://github.com/az9713/atlas-agent-tutorial/tree/main/ch09_agent_skills/skills/skill-security-audit
Command: npx skills add https://github.com/az9713/atlas-agent-tutorial --skill skill-security-audit-az9713

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Audit the agent's own skill library for malicious, misconfigured, or untrusted SKILL.md files. Use when you need to ensure the skill library is safe before enabling or sharing skills.

Core Features & Use Cases

  • Inventory and verify installed skills and their provenance.
  • Validate frontmatter fields (name, description) and check for risky configurations.
  • Detect prompt-injection risks and flag unsafe or untrusted SKILL.md content for remediation.

Quick Start

Start the audit by enumerating SKILL.md files across the library and reviewing their safety.

Frequently Asked Questions about skill-security-audit

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

FAQPage Schema
How do I audit my skill library for prompt-injection risks?

To audit for prompt-injection risks, the skill reviews SKILL.md files across local and shared repositories, detecting unsafe configurations and flagging untrusted content for remediation.

What is a SKILL.md security audit and when do I need it?

A SKILL.md security audit validates frontmatter fields and checks for malicious content in your skill library. You need it before enabling or sharing skills to ensure provenance and safety.

How do I validate frontmatter fields in installed skills?

You validate frontmatter fields by inventorying installed skills and verifying that required name and description fields are present and correctly configured, flagging any misconfigured files.

Can I check external skills for unsafe configurations before installing them?

Yes, you can check potential external skills by applying the audit to vendor-provided and self-authored SKILL.md files across shared repositories to detect risky configurations.

Does the skill audit log changes made to the skill library?

Yes, the skill audit logs changes while enumerating SKILL.md files across the library, ensuring a verifiable history of modifications during the safety review process.