Getting Started with Research Superpowers

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and ingests content from public third-party sources—explicitly PubMed E-utilities, the Semantic Scholar API, Unpaywall, and downloaded PDFs/open-access papers—and the agent is expected to read and extract information from those abstracts and full texts as part of screening and extraction, exposing it to untrusted third-party content that could contain indirect prompt injections.