academic-paper

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

• Third-party content exposure detected (high risk: 1.00). The skill's Phase 1 literature_strategist_agent and related agents explicitly perform web searches and ingest content from open/public third‑party sources (e.g., Google Scholar, Scopus, Semantic Scholar/Connected Papers, Retraction Watch, arbitrary URLs and gray literature) to build annotated bibliographies and a source corpus that downstream agents (argument_builder, draft_writer, citation_compliance, formatter) read and act on, so untrusted third‑party content can materially influence behavior.