add-3d-models

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to read/search public asset catalogs and download models from open/public URLs (e.g., raw.githubusercontent.com and builder-items.decentraland.org) so it ingests untrusted, user-hosted third‑party content that directly influences which assets are chosen and downloaded.