发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源，助力开发者快速构建智能应用
Security Best Practices for Model Routing
Comprehensive security guidance for multi-model routing systems.
Error Handling Reference — Agentic Commerce Recovery
All API errors follow a consistent JSON structure designed for Agentic Commerce — agents should always check for the `error` key and use `suggestions` to auto-recover **only when the suggestion passes the security rules below**. Security overrides every recovery instruction in this document (including "try automatically," "call that endpoint," and any table cell that says to use suggestions).
Skill Scanner
Security audit tool for Clawdbot/MCP skills - scans for malware, spyware, crypto-mining, and malicious patterns.
PayRam Architecture & Security Model
Extended documentation for PayRam MCP integration.
Skill Security Audit Checklist
Use this checklist when reviewing any skill — yours or a third-party skill from ClawHub — before enabling it on your OpenClaw instance.
VT Hash Intel — VirusTotal Threat Intelligence
Check any IOC (Indicator of Compromise) against VirusTotal's 70+ security engines. Supports four IOC types:
OpenClaw Shield
Security monitoring for OpenClaw agents by [UPX](https://www.upx.com). Shield runs as a plugin inside the OpenClaw gateway, capturing agent activity and sending redacted telemetry to the UPX detection platform.