literature-search

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly instructs searching and verifying papers on public sources (arXiv, IEEE Xplore, Google Scholar, Semantic Scholar) and extracting/verifying titles, authors, DOIs, which means the agent will fetch and interpret untrusted third-party web content that can influence citation verification and SOTA decisions.