data-source-connector

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 when the source type is excel/csv/parquet: scripts/introspect_source.py reads the user-supplied file contents (sheet cells / CSV rows / Parquet values) and places them into tables[].sampleRows and inferred schema fields, which are then included in the agent’s LLM context via data-model.json.