create-3d-avatar

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

• Third-party content exposure detected (medium risk: 0.30). In SKILL.md, the required runtime workflow sends user-supplied free-text prompt (and optionally outsider-supplied image_url) directly as JSON-RPC arguments to forge_avatar via https://three.ws/api/mcp-studio (tools/call), so the model ingests arbitrary outsider-authored text without selecting a specific trusted item first.