watch-video
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow downloads/derives subtitles/transcripts from a user-supplied VIDEO_URL (public web content via
yt-dlp) and writes their text intowatch_context.md, which the agent then opens/uses as LLM context (indirect prompt-injection risk from outsider-authored caption/subtitle text).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata