speech-to-text

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls belt app run infsh/fast-whisper-large-v3 with an audio_url (e.g., https://video.mp4), so the LLM context can ingest outsider-authored free text extracted from public web content fetched at runtime (the media’s transcript/captions).