backend-bulk-import

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests the user-uploaded CSV/Excel file contents (outsider-authored free text) via req.file.buffer → parseFile(...) and then uses the parsed rows/preview in subsequent processing, which would be available to any LLM context if the agent includes job/row data.