qwen-mm-plugins-blender

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

• Third-party content exposure detected (low risk: 0.10). The workflow runs Blender Python via execute_blender_code and imports/requests assets only through specific tool calls (e.g., search_sketchfab_models→download_sketchfab_model, search_polyhaven_assets→download_polyhaven_asset, and generate_hyper3d_model_via_text), so outsider-authored free text is only ingested if the agent actively selects/fetches specific external items rather than passively consuming arbitrary submissions.