edgeone-makers-migration

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

• Third-party content exposure detected (medium risk: 0.30). The runtime path defined by the skill is an HTTP request handler (e.g., agents/chat/index.ts / onRequest(context)), where outsider-authored free text is taken directly from context.request.body (such as message/text) and passed into the LLM as model input.