youtube-ingest
Warn
Audited by Snyk on Jul 30, 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 SKILL.md Step 1 (“Also fetch the page…”), the workflow performs a WebFetch on the canonical YouTube watch URL and asks the model to extract title/channel/topic from the page content derived from the user-supplied YouTube URL, which is outsider-authored.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata