watch
Warn
Audited by Snyk on Oct 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow watches user-supplied videos (via URL or local path) using yt-dlp and ffprobe/ffmpeg, extracting transcripts and frames which are subsequently ingested as untrusted evidence by the agent.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata