skills.rest
luiztrilha
luiztrilhaCOMMUNITY
Explore all skills by this author →
GitHub

skill-vetter

Identify security risks in AI agent skills via source checks and code reviews.

Updated Apr 27, 2026
Search Tags:#code review#risk assessment#security protocols#ai security#skill vetting
One-click install
npx skills add https://github.com/luiztrilha/dunderia-public --skill skill-vetter-luiztrilha
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: skill-vetter
Source: https://github.com/luiztrilha/dunderia-public/tree/main/templates/local-runtime-profile/skills/codex/skill-vetter
Command: npx skills add https://github.com/luiztrilha/dunderia-public --skill skill-vetter-luiztrilha

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill helps identify potential security risks and permission issues in AI agent skills before they are installed, providing a safety net against malicious or unsuitable code.

Core Features & Use Cases

  • Security-First Vetting: Checks for red flags, permission scope, and suspicious patterns.
  • Source Verification: Ensures the origin of the skill is known and reputable.
  • Code Review Protocol: Offers a step-by-step guide to manually review the skill's code.
  • Risk Classification: Rates the skill based on risk level for informed decisions.
  • Quick Vet Commands: Provides commands for vetting GitHub-hosted skills efficiently.

Quick Start

Run the skill-vetter command to begin vetting a new skill.

Frequently Asked Questions about skill-vetter

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

FAQPage Schema
How do I vet third-party AI agent skills for security risks before installation?▼

You can vet AI agent skills for security risks by performing source checks, code reviews, and permission scope evaluations. This process identifies red flags and suspicious patterns to ensure third-party skills are safe to deploy.

What is the best way to review code and permissions for a GitHub-hosted AI skill?▼

The best way to review GitHub-hosted AI skills is using quick vet commands that initiate a step-by-step code review protocol. This evaluates permission scopes and verifies the source origin to ensure the repository is reputable.

Can I classify the risk level of an AI agent skill based on its code?▼

Yes, you can classify the risk level of an AI agent skill by evaluating its source code and permission scopes. This risk classification rates the skill to help you make informed installation decisions based on identified security protocols.

When do I need to perform a source check on AI agent skills?▼

You need to perform a source check on AI agent skills before installing any third-party code. Verifying the origin ensures the source is known and reputable, preventing malicious or unsuitable code from compromising your environment.

Does skill vetting detect suspicious patterns in AI security protocols?▼

Yes, skill vetting detects suspicious patterns by applying a security-first approach to code review. It checks for red flags and evaluates permission scopes to validate the safety of AI security protocols within the skill.

Related Skills

Explore More Software Engineering Skills→
microsoftmicrosoft
1.4k

azure-app-onboard-prereq

Evaluate source code repositories for Azure deployment readiness.

Official
Advanced
binfen1binfen1

skill-vetter

Vet AI agent skills for security risks before installation.

Community
Advanced
LuisSambranoLuisSambrano
7

code-review

Perform systematic code review and static analysis across multiple programming languages.

Community
Advanced
LeoWSY-hashblueLeoWSY-hashblue
3

source-code-scanning

Scan source code for vulnerabilities, secrets, and dependency CVEs.

Community
Advanced