make-video

Warn

Audited by Snyk on Feb 26, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md shows the tool requires an arbitrary --image-source URL (example usage and parameter docs), so the agent will fetch and ingest images from open/public third-party sites and use their content to drive video-generation decisions, exposing it to untrusted user-provided content that could indirectly influence behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 26, 2026, 03:48 AM