creative-image-generator
Warn
Audited by Snyk on Feb 16, 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 accepts a user-provided reference image (passed as reference_image_path / "Пользователь может приложить изображение-референс") which the agent reads and uses to extract colors/composition, so it ingests and interprets arbitrary user-generated third-party content.
Audit Metadata