add-3d-models

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to read external catalogs and search/download public assets (see SKILL.md lines directing to "{baseDir}/../../context/asset-packs-catalog.md" and "{baseDir}/../../context/open-source-3d-assets.md" and example curl commands fetching from builder-items.decentraland.org and raw.githubusercontent.com), which causes the agent to ingest and act on untrusted, user/third‑party web content when selecting and downloading models.