molfeat

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

• Third-party content exposure detected (high risk: 0.80). The skill's ModelStore and PretrainedMolTransformer explicitly load pretrained models and model cards from external hubs (e.g., HuggingFace / GitHub / external URLs) and call model_card.usage() / store.load(), which means the agent will ingest and display untrusted, user-uploaded third-party content (model cards and hosted models).