alterlab-rma-literature-reviewer

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

• Third-party content exposure detected (high risk: 0.80). The skill's Agentic Protocol and Workflow explicitly direct the agent to "search the web" and to use public databases and resources (e.g., Google Scholar, JSTOR, Scopus, arXiv/preprint servers) so the agent will fetch and read open/public third‑party content that can influence its search, screening, and synthesis actions.