paper-search

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

• Third-party content exposure detected (high risk: 0.70). The required workflow delegates to the literature-engine/literature-search skill via the “Import — strictly follow” directive, which at runtime likely fetches and summarizes external/public paper text (outsider-authored free-form content) into the agent’s LLM context through that sub-skill’s get_paper_content call.