← Back to Skills Marketplace
Skill Vetter
by
spclaudehome
· GitHub ↗
· v1.0.0
265452
Downloads
1269
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install skill-vetter
Description
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
Usage Guidance
Safe to install as a manual vetting aid. When using it, only fetch repositories you intentionally want to review, replace placeholders carefully, and treat downloaded skill text as untrusted content.
Capability Analysis
Type: OpenClaw Skill
Name: skill-vetter
Version: 1.0.0
This skill, 'skill-vetter', is designed to help AI agents identify security risks in other skills. The `SKILL.md` file outlines a vetting protocol, including a comprehensive list of 'RED FLAGS' for agents to look for in untrusted code. The 'Quick Vet Commands' section uses `curl` to fetch metadata and file contents from GitHub (api.github.com, raw.githubusercontent.com) for *other* skills, which is directly aligned with its stated purpose of vetting. There is no evidence of malicious intent, data exfiltration, or harmful prompt injection against the agent itself; rather, it instructs the agent on how to detect such behaviors in external skills.
Capability Assessment
Purpose & Capability
The stated purpose is security vetting of AI-agent skills, and the artifact contains review steps, red-flag criteria, risk classification guidance, and reporting format consistent with that purpose.
Instruction Scope
It tells agents to read all files in a target skill and includes curl examples for GitHub-hosted skills; that is expected for vetting, but reviewed files should be treated as untrusted evidence rather than instructions.
Install Mechanism
The package artifact available for review is a single Markdown SKILL.md with no executable scripts, dependencies, installers, or setup hooks.
Credentials
The only environment interaction described is optional network fetching from api.github.com and raw.githubusercontent.com for user-selected repositories, which is proportionate to source and code review.
Persistence & Privilege
The artifact does not request persistence, background workers, elevated privileges, credential stores, browser sessions, or system modification.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install skill-vetter - After installation, invoke the skill by name or use
/skill-vetter - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - Security-first skill vetting for AI agents
Metadata
Frequently Asked Questions
What is Skill Vetter?
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns. It is an AI Agent Skill for Claude Code / OpenClaw, with 265452 downloads so far.
How do I install Skill Vetter?
Run "/install skill-vetter" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Skill Vetter free?
Yes, Skill Vetter is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Skill Vetter support?
Skill Vetter is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Skill Vetter?
It is built and maintained by spclaudehome (@spclaudehome); the current version is v1.0.0.
More Skills