url-transcript
Warn
Audited by Snyk on Jul 2, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The workflow fetches outsider-authored free text from the target URL at runtime (e.g., HTML/player config and especially embedded/official captions/transcripts via
curl/yt-dlp --write-subs), which is then ingested into the agent context as transcript text for further processing/output.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata