huggingface-import

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow (SKILL.md Step 1: "Navigate to the HuggingFace source" and find data files) instructs the agent to fetch and analyze datasets from public HuggingFace repositories/spaces/datasets, which are untrusted, user-contributed content that can directly influence mapping, CSV generation, and subsequent actions.