doc-parser

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

• Third-party content exposure detected (high risk: 0.85). The required workflow is to parse a user-provided document (e.g., via converter.convert("document.pdf") and then doc.export_to_markdown()/export_to_text()), so any outsider-authored document text (PDF/Word/HTML/images) becomes readable free text in the agent’s LLM context.