mirror of
https://github.com/LeoYeAI/openclaw-master-skills.git
synced 2026-08-14 00:48:08 +00:00
Bulk import from openclaw/skills official Archive (⭐3,600+).
Quality filter: SKILL.md 800B-30KB with proper YAML frontmatter.
Coverage areas:
- Crypto / Web3 / DeFi / Trading bots
- Feishu / DingTalk / Enterprise WeChat
- Business systems (freelance ops, performance eng, legal docs)
- Document templates / PPT design / OCR
- Email / CRM / Customer service
- Financial analytics / Stock trading
- AI tools / Agent collaboration / Model management
GoPlus AgentGuard
AI Agent Security Guard — protect your AI agents from dangerous commands, data leaks, and malicious skills.
Features
- Code Scanning — 24 detection rules covering shell injection, credential leaks, prompt injection, Web3 exploits, and more
- Action Evaluation — Real-time allow/deny/confirm decisions for runtime actions (network, exec, file, Web3)
- Trust Registry — Manage skill trust levels with capability-based access control
- Security Patrol — Automated daily security checks for OpenClaw environments
- Audit Logging — Full security event trail with reporting
Usage
/agentguard scan <path> — Scan code for security risks
/agentguard action <description> — Evaluate runtime action safety
/agentguard patrol [run|setup|status] — Daily security patrol
/agentguard trust <subcommand> — Manage skill trust levels
/agentguard report — View security event audit log
/agentguard config <level> — Set protection level (strict/balanced/permissive)
Requirements
- Node.js 18+
- Optional: GoPlus API credentials for enhanced Web3 transaction simulation
Author
Built by GoPlus Security — the leading Web3 security infrastructure provider.