doubao

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow for this skill is calling Doubao vendor TTS/ASR endpoints and ingesting the HTTP/SSE response body (chunked JSON objects / SSE data: events) into the agent’s context; those response payloads are vendor-authored free text/JSON fields (e.g., sentence, result.text, error message), which are outsider content.