hugging-face-evaluation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly loads and parses arbitrary, public Hugging Face README content via ModelCard.load(card.content) (e.g., https://huggingface.co/<repo_id>) and also fetches data from the public Artificial Analysis API (https://artificialanalysis.ai/api/...), both of which are untrusted, user-generated third‑party sources that the tool reads and interprets as part of its workflow.