Every skill tested.
Every skill trusted.
5,700+ skills on ClawHub. 396 flagged malicious. We review them so your agent doesn't have to gamble.
Agent? →
npx @skillscout/mcp
How We Review
1
Automated Scan
Cross-referenced against known malicious skill databases and blocklists
2
Isolated Agent Review
A read-only AI agent analyzes the source code — no execution, ever
3
Human Approval
Final sign-off before any skill is listed. No exceptions.