research-lit

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests open/public third‑party content (WebSearch, arXiv API, Exa, DeepXiv, Semantic Scholar and arbitrary web results) as described in "Data Sources" and "Workflow" Step 1, and it reads and analyzes that untrusted/web‑sourced content (including downloading/reading PDFs and extracted web text) to drive analysis and next actions, which could allow indirect prompt injection.