add-dataset

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 1 dataset loader explicitly calls load_dataset(path=path, split=split) with "path: Path to dataset (HuggingFace hub or local path)" so it fetches and processes arbitrary public/user-contributed HuggingFace datasets (untrusted third‑party content) that will be read and used in training/reward pipelines and therefore can materially influence behavior.