skill-vetter-liomiSecurity-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope,...
Install via ClawdBot CLI:
clawdbot install liomichan/skill-vetter-liomiGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Potentially destructive shell commands in tool definitions
eval(Uses known external API (expected, informational)
api.github.comAudited Apr 17, 2026 · audit v1.0
Generated May 5, 2026
A marketplace for AI agent skills needs to automatically vet submissions from independent developers. This skill package can be used to check each skill for red flags, permission scope, and suspicious patterns before listing, ensuring ecosystem safety.
Enterprises deploying AI agents for internal tasks must vet all third-party skills to prevent data exfiltration or unauthorized system access. This package provides a standardized protocol for security teams to review skills before allowing installation on corporate agent systems.
Open source AI agent communities can use this vetting package to create a peer-review process for shared skills. Contributors submit vetting reports, reducing risk for all users and building trust in community repositories.
Financial institutions using AI agents for trading or data handling must comply with strict security regulations. This skill can automate the vetting of agent skills to ensure they meet compliance requirements, especially regarding credential handling and network permissions.
Individuals who run personal AI assistants can use this package to critically evaluate skills before installation, protecting sensitive local data such as SSH keys, browser sessions, or personal documents from malicious or poorly-designed skills.
Offer automated skill vetting as a subscription product to AI agent skill marketplaces. Each marketplace pays a fee per skill vetted or a monthly subscription, ensuring their listings are safe and trustworthy.
Integrate this vetting package into enterprise agent management platforms as a premium security add-on. Companies pay per-audit or an annual license to automatically vet all skills deployed in their environment.
Release the core vetting logic open-source but offer paid tiers for dedicated support, custom rule sets, and integration assistance for organizations needing advanced security policies.
💬 Integration Tip
Integrate the vetting protocol as a pre-installation hook in your agent framework, invoking it automatically when a new skill is downloaded. Use the provided output format for logging and alerting.
Scored Jun 29, 2026
Meta-skill for AI agent self-improvement. Analyzes runtime logs to detect error patterns, regressions, and inefficiencies, then generates structured improvem...
Stop waiting for prompts. Keep working.
Turn OpenClaw into a learning-loop agent with seeded workspace rules, skill promotion, reflective memory, and proactive maintenance.
Meta-agent skill for orchestrating complex tasks through autonomous sub-agents. Decomposes macro tasks into subtasks, spawns specialized sub-agents with dynamically generated SKILL.md files, coordinates file-based communication, consolidates results, and dissolves agents upon completion. MANDATORY TRIGGERS: orchestrate, multi-agent, decompose task, spawn agents, sub-agents, parallel agents, agent coordination, task breakdown, meta-agent, agent factory, delegate tasks
Complete toolkit for creating autonomous AI agents and managing Discord channels for OpenClaw. Use when setting up multi-agent systems, creating new agents, or managing Discord channel organization.
Billions decentralized identity for agents. Link agents to human identities using Billions ERC-8004 and Attestation Registries. Verify and generate authentic...