Skill Claude CodeCodex
7-layer AI security + ML detection for OpenClaw. Covers all 10 OWASP Agentic AI risks — prompt injection, tool misuse, memory poisoning, data exfiltration, and more — across ALL channels (Signal, Telegram, Discord, WhatsApp, web) simultaneously.
MCP server Claude CodeCodexCursor
AI Agent Security System - 7-layer defense against prompt injection, data exfiltration, and AI-specific attacks. Runs locally from the zugashield Python package.
Zuga-Technologies/agentpool-mcp
MCP server Claude CodeCodexCursor
MCP server "agentpool", hosted remotely at agentpool-mcp-production.up.railway.app, as configured in Zuga-Technologies/agentpool-mcp.