network-meta-analysis-appraisal

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

• Third-party content exposure detected (high risk: 0.90). The skill directly ingests arbitrary external PDFs supplied to scripts/pdf_intelligence.py (e.g., "python scripts/pdf_intelligence.py path/to/nma_paper.pdf") and then semantic_search.py reads and interprets the extracted text for evidence matching, so it processes untrusted third‑party/user‑provided content as part of its workflow.