vaex

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

• Third-party content exposure detected (high risk: 0.70). The skill's I/O documentation explicitly shows loading data and state from third-party locations (e.g., vaex.open('s3://bucket-name/data.parquet'), vaex.open('gs://bucket-name/data.parquet'), vaex.open('ws://hostname:9000/data') and df.state_load('state.json') in references/io_operations.md), which means untrusted external files/state can be ingested and can restore transformations/models that materially influence subsequent operations.