huggingface-best

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

• Third-party content exposure detected (medium risk: 0.30). SKILL.md’s runtime workflow queries Hugging Face API endpoints to read benchmark dataset lists and leaderboard entries (e.g., /api/datasets?... and /leaderboard) and model metadata from model endpoints, which are outsider-authored free text in dataset/model cards and leaderboard content when ingested for parsing/display.