idea-discovery

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 1 (/research-lit) and Phase 3 (/novelty-check) explicitly search and ingest content from public sources (arXiv, Google Scholar, Semantic Scholar) and can optionally download arXiv PDFs via the ARXIV_DOWNLOAD flag, and that external content is parsed and used to drive idea selection and pipeline decisions, exposing the agent to untrusted third‑party content that could carry indirect prompt injection.