watch
Warn
Audited by Snyk on Aug 22, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In the /watch runtime, the agent ingests outsider-authored free text derived from user-supplied video content by downloading/processing “any yt-dlp-supported site” or direct URLs/HLS/DASH and then reading OCR text and transcripts from extracted frames and captions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata