rig-a-model

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

• Third-party content exposure detected (medium risk: 0.30). The skill takes a user-supplied glb_url and submits it to three.ws (/api/mcp-studio / /api/forge?action=rig) where an external model file may be fetched and processed, so outsider-authored content can influence runtime inputs via the provided URL (indirect prompt injection via file/content ingestion rather than free text).