blender-mcp-setup

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

• Third-party content exposure detected (low risk: 0.10). The required workflow reads the scene's file path, object names, and viewport screenshot from the Blender session, which could contain outsider-authored text only if the user opens an untrusted .blend, so the agent must first load that file and the skill itself gates that case through blender-content-safety-and-privacy.