hugging-face

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to fetch and inspect content from public Hugging Face Hub endpoints (e.g., https://huggingface.co/api/models, /api/datasets, /api/spaces and router.huggingface.co) which return community/user-generated models, datasets and spaces that the agent is expected to read and then use (e.g., to choose models and run inferences), so untrusted third-party content can meaningfully influence actions.