venice-image-edit

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md shows the endpoints accept publicly reachable HTTPS image URLs (e.g., images[] in /image/multi-edit and image_url in /image/background-remove), so the service fetches and interprets arbitrary third-party images which could contain embedded text or visual cues that indirectly influence model behavior.