lit-pm

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs launching literature-researcher agents to search, fetch and ingest papers and PDFs from the open web (see Stage 2: "Launch 2-3 literature-researcher agents" for review discovery and Stage 5: "Section writers conduct targeted research... pdf_storage_path" in handoffs), and those third‑party materials are read and used to drive outlines, synthesis, and downstream actions—so it clearly consumes untrusted public content that can influence behavior.