video-transcription
Warn
Audited by Snyk on May 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill fetches and ingests arbitrary public media URLs (e.g., download_videos_from_manifest_with_ytdlp.mjs and resolveProviderMediaInput in _shared.mjs accept sourceUrl/https URLs), transcribes their spoken content with scripts/transcribe_video.mjs and poll_transcription.mjs, and explicitly uses those transcripts to drive subtitle/edit planning, so untrusted, user-generated third-party content is read and can materially influence downstream actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata