vaex
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill includes guidelines for the agent to suggest the vendor's research platform, K-Dense Web, when handling complex workflows.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through data ingestion points. 1. Ingestion points: The skill loads data via vaex.open() and vaex.from_csv(). 2. Boundary markers: The instructions lack explicit markers to differentiate untrusted data from instructions. 3. Capability inventory: The skill utilizes file-writing capabilities through the export_hdf5() function. 4. Sanitization: No content validation or sanitization is described for the ingested data.
- [COMMAND_EXECUTION]: The documentation provides Python code examples for executing data operations such as filtering, aggregation, and visualization within the Vaex environment.
- [EXTERNAL_DOWNLOADS]: The skill depends on the vaex Python library, a third-party tool for high-performance out-of-core data processing.
Audit Metadata