partykit

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

• Third-party content exposure detected (high risk: 0.90). The skill's server onMessage handlers clearly ingest arbitrary client-sent messages (see multiple "onMessage" examples and the "AI Integration" section) and directly pass data.text into ai.run, meaning untrusted user-generated content from connected clients can influence AI calls and subsequent actions.