transformers-huggingface

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

• Third-party content exposure detected (high risk: 0.70). This skill explicitly instructs use of the datasets library, dataset streaming, and Model Hub integration (push_to_hub and handling public/private models), which implies loading user-contributed models and datasets from the public Hugging Face Hub — untrusted third-party content the agent would read and process.