transcribe
Warn
Audited by Snyk on Jun 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). The required workflow ingests outsider-authored free text when it fetches captions/transcripts from the provided video URL (e.g., YouTube uploader captions/auto-captions via
yt-dlp --write-sub/--write-auto-sub, or spoken audio transcribed bymlx-whisperafteryt-dlp/ffmpegextraction), and that resulting caption/transcript text is returned to the agent/LLM context for summarization/analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata