zynna-analyze-video
Warn
Audited by Snyk on Apr 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill posts the provided TikTok URL to the Zynna Open Skills API (see SKILL.md step 2 and lib/analyze-video.js -> client.analyze which calls /api/open/skills/analyze via lib/zynna-client.js) and ingests transcripts, vision scenes, and response/suggestions derived from user-generated TikTok content, which are persisted and can materially influence follow-up decisions or tool handoffs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata