dataset-transformation

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow can ingest outsider-authored free text from the user-provided dataset itself (Step 5/7/9: it reads 1–2 sample records and later loads the full JSONL via pd.read_json(..., lines=True)), and those records are not authored by the operating user/organization by definition.