harmony-models

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

• Third-party content exposure detected (low risk: 0.10). The required workflow only reads outsider-authored text when the agent fetches specific packs from public asset libraries (Kenney, Quaternius, Poly Haven, or other stores the developer picks), which is the low-risk "search/fetch selected content" path, while the code, procedural, and generator paths ingest no outsider text.