add-model-descriptions

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches model IDs from the public HuggingFace router (https://router.huggingface.co/v1/models) and requires researching each missing model by searching the open web for specifications, meaning the agent will ingest and act on untrusted, user-generated third-party content as part of its workflow.