using-huggingface

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly loads models, datasets, and Spaces from the public HuggingFace Hub (e.g., load_dataset("imdb"), AutoModel.from_pretrained(...), HfApi.list_models, and the api-inference endpoint) as shown in SKILL.md, which are user-uploaded/public resources and can materially change model behavior or downstream actions.