hugging-face-paper-publisher

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and indexes papers from public arXiv pages and reads/writes public Hugging Face repository READMEs/paper pages (see the "index", "search", "info", and "link" commands in SKILL.md), thus ingesting untrusted, user-generated third-party web content that can influence tagging, linking, and subsequent tool actions.