hugging-face-dataset-creator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs the agent to use the HF MCP Server for "Discovery" (e.g., calls like search_datasets and get_dataset_details) to retrieve public Hugging Face dataset metadata and content — untrusted, user-generated third‑party material that the agent is expected to read and that can change subsequent dataset creation/configuration actions.