teach-from-paper

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow reads the user-supplied paper file ($0) end-to-end (including via pdftotext for PDFs) and then injects its extracted prose into the agent context; if that paper is authored by an outsider, its body text becomes LLM-readable context (outsider-authored document ingestion path).