hugging-face-paper-publisher

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

• Third-party content exposure detected (high risk: 0.80). The skill fetches and ingests public, user-provided content—e.g., downloading arbitrary repository README.md via hf_hub_download and calling public pages/APIs like https://huggingface.co/papers/{arxiv-id} and the arXiv API—so the agent will read and interpret untrusted third‑party content as part of its workflow.