extracting-pdf-text

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

• Third-party content exposure detected (high risk: 0.90). The skill's Mistral OCR pipeline (scripts/extract_mistral_ocr.py) explicitly accepts URL inputs and calls client.ocr.process with "document_url", causing the agent to fetch and extract markdown from arbitrary public PDFs (untrusted third‑party content) which is then consumed by the LLM pipeline.