hugging-face-paper-pages

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses public Hugging Face paper pages (e.g., https://huggingface.co/papers/{PAPER_ID}.md) and arXiv pages (https://arxiv.org/abs/{PAPER_ID}), which are user-submitted/public third‑party sources that the agent is instructed to read and use when summarizing or analyzing papers, so untrusted content could influence its behavior.