biorxiv-database

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

• Third-party content exposure detected (high risk: 0.80). The skill directly fetches and ingests public, user-submitted preprint content (titles, abstracts, metadata via https://api.biorxiv.org and full-text PDFs/HTML from https://www.biorxiv.org) which the agent reads and processes as part of searches and downloads, exposing it to untrusted third‑party content that could carry indirect prompt injections.