speech-to-text

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

• Third-party content exposure detected (high risk: 0.80). The skill accepts and transcribes audio from arbitrary public sources (e.g., the realtime server-side "url" parameter in references/realtime-server-side.md and the cloud_storage_url option in references/transcription-options.md), meaning untrusted public/user-provided audio would be read and interpreted as part of its workflow and could carry indirect prompt injection.