gemini-video-understanding
Warn
Audited by Snyk on Oct 6, 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 skill processes YouTube URLs and external video files provided by the user, which can contain untrusted transcripts or visual text ingested at runtime by the Gemini model, representing low-risk indirect prompt injection via fetched/selected media.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata