hugging-face-gradio

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

• Third-party content exposure detected (high risk: 0.90). The skill's "Prediction CLI" section in SKILL.md documents using gradio info <space_id_or_url> and gradio predict <space_id_or_url> ..., which instructs the agent to fetch and parse arbitrary Hugging Face Spaces (public, user-generated) and then act on the returned endpoint definitions/results, enabling untrusted third-party content to influence tool use.