pixverse-ai-image-and-video-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts arbitrary HTTPS URLs and streams/passes remote web content into generation workflows (see capabilities/create-and-edit-image.md --image , capabilities/create-video.md --image , and capabilities/asset-management.md asset upload "https://..."), so untrusted third-party content from the open web can be ingested and influence subsequent model outputs and actions.