hugging-face-cli

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and inspects public, user-generated content from the Hugging Face Hub (models/datasets/spaces) via commands listed in SKILL.md such as "hf download", "hf models info", "hf datasets info", and "hf spaces info", which the agent is expected to read/interpret and which can materially affect subsequent downloads, compute jobs, or deployments.