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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 26, 2026, 04:17 AM
Issues
1
Security Audit — snyk — video