← Back to Skills Marketplace
17508
Downloads
9
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install skill-vetting
Description
Vet ClawHub skills for security and utility before installation. Use when considering installing a ClawHub skill, evaluating third-party code, or assessing w...
Usage Guidance
Install this if you want an agent-assisted scanner for reviewing OpenClaw skills. Expect it to read local skill artifacts and run scanner logic; review any requested shell or network action before approving it, especially if pointed at private files or remote sources.
Capability Analysis
Type: OpenClaw Skill
Name: skill-vetting
Version: 1.1.0
This skill bundle is a security scanner designed to vet other OpenClaw skills for malicious patterns and prompt injection. The `SKILL.md` and `ARCHITECTURE.md` files explicitly warn against prompt injection and provide instructions for the AI agent on how to identify and reject such attempts. The `scripts/scan.py` file implements the detection logic for various security risks, including prompt injection, but does not exhibit any malicious behavior itself. All files are aligned with the stated purpose of security vetting and show no evidence of intentional harmful behavior, data exfiltration, unauthorized execution, or persistence mechanisms.
Capability Assessment
Purpose & Capability
The described files and runtime behavior align with a skill whose purpose is to scan other OpenClaw skills for prompt injection and malicious patterns.
Instruction Scope
The security-oriented instructions are scoped to evaluating skill artifacts and rejecting untrusted instructions found inside artifacts, which fits the stated purpose.
Install Mechanism
SkillSpector noted missing explicit permission declarations for file reads, shell execution, and network use; that is a transparency gap, but those capabilities are expected for a local security scanner.
Credentials
Local file inspection and scanner execution are proportionate to vetting skill bundles; no artifact-backed evidence shows unrelated data access, exfiltration, or destructive behavior.
Persistence & Privilege
No supplied evidence indicates background persistence, privilege escalation, credential harvesting, or automatic long-running execution outside user-directed scanning.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install skill-vetting - After installation, invoke the skill by name or use
/skill-vetting - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.0
Security: Expanded file scanning (html/env/ts/etc) + 5 new prompt injection patterns. Features: JSON output, severity levels, color-coded findings. Docs: AI reviewer hardening + defense architecture.
v1.0.1
- Added SKILL.md.backup file for backup or versioning purposes.
- No changes to core functionality or documentation content.
- The skill continues to provide security and utility vetting guidance for ClawHub skills.
v1.0.0
Initial release - Automated security scanner + malicious pattern database + complete vetting workflow for ClawHub skills
Metadata
Frequently Asked Questions
What is Skill Vetting?
Vet ClawHub skills for security and utility before installation. Use when considering installing a ClawHub skill, evaluating third-party code, or assessing w... It is an AI Agent Skill for Claude Code / OpenClaw, with 17508 downloads so far.
How do I install Skill Vetting?
Run "/install skill-vetting" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Skill Vetting free?
Yes, Skill Vetting is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Skill Vetting support?
Skill Vetting is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Skill Vetting?
It is built and maintained by Eddy (@eddygk); the current version is v1.1.0.
More Skills