skill-checker-janeSecurity-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 janeaaaa/skill-checker-janeGrade 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 25, 2026 · audit v1.0
Generated Oct 6, 2026
A developer discovers a new skill on ClawdHub that promises to automate file organization. Before installing, they run Skill Vetter to inspect source reputation, review all code files for red flags, and assess whether the skill requests unnecessary credentials or network access. This prevents a potentially malicious install and documents the vetting decision for future reference.
An AI operations team wants to adopt shared skills from an open-source GitHub repository. They use Skill Vetter's quick vet commands to pull repository stats, list skill files, and fetch SKILL.md for review. The team applies the risk classification table to decide which skills need human approval before deployment.
In a multi-agent environment, an agent receives a skill package from an unknown peer agent. It applies Skill Vetter to check for obfuscated code, base64 decoding, and accesses to sensitive files like MEMORY.md or ~/.ssh. The agent either rejects the skill or escalates to a human based on the vetting report.
A platform operator integrates Skill Vetter as a mandatory gateway for all skills uploaded to their agent marketplace. Every submission is automatically scanned for red flags like curl to unknown URLs, eval with external input, and credential requests. Skills that fail are blocked or flagged for manual review, protecting end users from malicious packages.
A fintech company requires all AI agent skills to undergo a documented security review before use. The compliance team uses Skill Vetter to produce standardized vetting reports that capture source, permissions, risk level, and verdict. These reports are stored as audit evidence for regulators and internal security policies.
Skill Vetter is distributed freely as an open-source skill, building trust and community adoption. The maintainers offer paid enterprise support, including custom red-flag rulesets, integration assistance, and priority updates. Revenue comes from support contracts and consulting services.
A cloud service wraps Skill Vetter's logic into an API and dashboard that automatically scans skills from marketplaces, GitHub, and other sources. Teams pay a monthly subscription based on the number of skills vetted and users. The platform provides audit logs, alerts, and compliance reports.
Skill Vetter is licensed as a module within a broader AI security suite sold to large organizations. It integrates with existing SIEM and CI/CD pipelines to enforce vetting policies before skill deployment. Licensing is annual per-seat or per-node, with premium features like custom risk scoring.
💬 Integration Tip
Embed Skill Vetter into your skill installation pipeline as a mandatory pre-install check, and customize the red-flag list to match your organization's security policies for immediate protection.
Scored Oct 6, 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...