huggingface-datasets

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests outsider-authored dataset contents at runtime via the Hugging Face Dataset Viewer endpoints /first-rows, /rows, /search (query text), and /filter after resolving dataset/config/split through /splits, and then reading returned row text/strings for exploration/extraction.