huggingface-paper-publisher

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

• Third-party content exposure detected (high risk: 0.70). This skill fetches and parses public, user-authored content at runtime (requests to the arXiv API in scripts/paper_manager.py:get_arxiv_info and HTTP requests to https://huggingface.co/papers/* plus hf_hub_download of arbitrary repository README.md in link_paper_to_repo), and it reads/interprets that untrusted content to generate citations and modify/upload repository READMEs, so third-party content can materially influence its actions.