paper-search

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests search results and snippets from Google Scholar via the Serper API (see "Results sourced from Google Scholar via Serper API" in SKILL.md), so the agent will read and act on untrusted third-party content that could materially influence decisions.