1. The skill are processed on an internal engine which runs on three things; skills.md, VirusTotal scanning,LLM Source scanning, Dev reputation, Skill installs and running regex detections and crafting overall safety score in most accurate and least noisy way possible. I agree there will be scope for improvement
2. pattern matching and trying to match the purpose of skill, do you have any suggestion for me?
3. We have launched a skill here that you can install and provide our token and you will be able to see your instance security in the dashboard
I am a web security researcher and bug bounty hunter and felt like this is something we all needed when running OpenClaw skills and instances. Completely free and runs LLM on public source code.