3d-model-generation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and processes arbitrary public URLs (e.g., the "Image-to-3D Conversion" example with image_urls in SKILL.md) and documents web_search/web_search_citations SSE events, so the agent ingests untrusted third-party content (images and web search results) that can influence generation and subsequent tool actions.