doc-intel-llm-tier-pl

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

• Third-party content exposure detected (medium risk: 0.30). The runtime path scripts/ekstrakcja_llm.py ingests raw, outsider-authored free text from user-provided files via --text/--docx into Document(raw_text=raw_text) and then llm.extract_all(doc), which is the workflow’s core LLM grounding step.