neqsim-process-extraction

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

• Third-party content exposure detected (medium risk: 0.65). The skill ingests outsider-authored free text when the runtime input is a .docx/text document containing paragraphs/tables from external parties; the workflow then parses that text (e.g., doc.paragraphs / table.rows via python-docx) and converts it into JSON/LLM context for extraction, which is an indirect prompt-injection risk from outsider content.