← Back to Skills Marketplace
janeaaaa

Skill Vetter 1.0.0

by janeaaaa · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
73
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install skill-checker-jane
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,...
Usage Guidance
This skill is an instruction-only vetting checklist and appears internally consistent and low-risk. Before relying on it: 1) recognize it expects the agent to fetch and read repo files (GitHub network access); confirm you’re comfortable allowing those reads in your environment; 2) treat its output as an aid, not a replacement for human review—it flags patterns but cannot guarantee absence of hidden behavior; and 3) if you use the quick commands, ensure the agent’s network permissions and credentials for GitHub (if any) are scoped appropriately. Install only if you accept outbound repo reads and the agent’s autonomy to run the described checks.
Capability Analysis
Type: OpenClaw Skill Name: skill-checker-jane Version: 1.0.0 The skill bundle 'skill-checker-jane' (skill-vetter) is a security utility designed to provide a structured vetting protocol for AI agents to evaluate other skills. The instructions in SKILL.md promote security best practices, such as checking for data exfiltration, unauthorized credential access, and obfuscated code. The included shell commands are limited to querying the official GitHub API for repository metadata, which is consistent with the tool's stated purpose of verifying skill sources.
Capability Assessment
Purpose & Capability
Name and description (skill vetting) match the content of SKILL.md: it's a checklist and actionable commands for reviewing skills. It requests no credentials, binaries, installs, or config paths—proportionate for a vetting tool.
Instruction Scope
SKILL.md instructs the agent to read all files in a candidate skill and to run network queries (GitHub API / raw content) when evaluating GitHub-hosted skills. This is coherent for vetting, but implies the agent will access remote repos and potentially arbitrary repository files — ensure network access and repository read access are acceptable in your environment and that the agent won’t automatically exfiltrate reviewed content.
Install Mechanism
No install spec and no code files — lowest-risk model for disk persistence. Nothing will be downloaded or executed by an installer as part of this skill package.
Credentials
The skill declares no required environment variables or credentials, which is appropriate. However the vetting steps assume outbound network access (to api.github.com and raw.githubusercontent.com) and the ability to read repository files; those are operational permissions rather than secret credentials and should be allowed only if acceptable to you.
Persistence & Privilege
always is false and the skill does not request persistent system changes or modify other skills. Model invocation is allowed (default) which is normal for skills of this nature.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install skill-checker-jane
  3. After installation, invoke the skill by name or use /skill-checker-jane
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of skill-vetter, a security-first protocol for vetting AI agent skills. - Provides a detailed vetting checklist covering source, code review, permission scope, and risk classification. - Includes a list of red flags to watch for in skill code, with clear reject criteria. - Outlines a standardized reporting format for vetting outcomes. - Supplies quick commands for evaluating skills hosted on GitHub. - Establishes a trust hierarchy and reaffirms best security practices. - Designed to be used before installing any external skill.
Metadata
Slug skill-checker-jane
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Skill Vetter 1.0.0?

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,... It is an AI Agent Skill for Claude Code / OpenClaw, with 73 downloads so far.

How do I install Skill Vetter 1.0.0?

Run "/install skill-checker-jane" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Skill Vetter 1.0.0 free?

Yes, Skill Vetter 1.0.0 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Skill Vetter 1.0.0 support?

Skill Vetter 1.0.0 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Skill Vetter 1.0.0?

It is built and maintained by janeaaaa (@janeaaaa); the current version is v1.0.0.

💬 Comments