ops-huggingface

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow reads outsider-authored free text from the Hugging Face Hub via its read-only commands that take user-supplied search/query/repo inputs and then ingest remote listing/metadata fields for output (e.g., HfApi().list_models(...), HfApi().list_datasets(...), HfApi().repo_info(...), HfApi().list_repo_files(...)).