hugging-face-paper-publisher

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

• Third-party content exposure detected (high risk: 0.70). The skill's CLI and scripts (scripts/paper_manager.py) fetch and parse public, user-generated content — downloading arbitrary repository README.md via hf_hub_download and querying public pages/APIs (https://huggingface.co/papers/{id} and the arXiv API via requests.get in index_paper/check_paper/get_arxiv_info) and then read/interpret that content to decide how to update READMEs and produce commits, so untrusted third‑party content can materially influence tool behavior.