websockets-realtime

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

• Third-party content exposure detected (high risk: 0.70). The skill's examples show the agent reading and acting on arbitrary user-generated messages (e.g., ws.onmessage / EventSource.onmessage parsing event.data, Redis pub/sub channels like "user-messages", and broadcast handlers), which ingests untrusted third-party content (chat/posts) as part of its runtime workflow.