3d-model-generation

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests arbitrary public URLs (e.g., the Image-to-3D example uses "image_urls": ["https://example.com/product-image.jpg"]) and documents web search events/web_search_citations in SSE (SKILL.md and references/SSE-EVENTS.md), showing the agent will fetch and act on untrusted third-party web content that can influence generation decisions.