video
Warn
Audited by Snyk on Aug 26, 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). SKILL.md’s “Reverse-Engineer a Viral Edit” workflow instructs the agent to pull a user-supplied reference via tools like watch-video or social-fetch, which requires ingesting free-text/caption content and multimodal frames from an externally authored video/post at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata