hugging-face-cli

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly instructs use of the hf CLI to download and browse models, datasets, and spaces from the public Hugging Face Hub (see "Download" and "Browse Hub" sections), which are user-uploaded/untrusted third-party content that the agent would ingest and that could influence subsequent actions.