vaex
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): The skill contains instructional content for the Vaex library. Analysis did not reveal any malicious patterns, prompt injections, or unauthorized data access.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill ingests external data (CSV/HDF5), this is standard for data analysis and does not present an unusual risk in this context. Evidence Chain: 1. Ingestion points: vaex.open() and vaex.from_csv() in SKILL.md and core_dataframes.md. 2. Boundary markers: Absent. 3. Capability inventory: File reading (vaex.open) and file writing (df.export_hdf5). 4. Sanitization: Absent.
Audit Metadata