networking

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill runs WebSocket and UDP servers that accept and JSON-parse messages from arbitrary external clients (see handleMessage in SKILL.md and assets/websocket-server.js and the UDP socket.on('message') handler), so it ingests untrusted user-generated content that the agent reads and acts on.