parquet-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external Parquet files, which serves as a potential surface for indirect prompt injection if the files contain malicious content.\n
- Ingestion points: The scripts
scripts/analyze.pyandscripts/template.pyutilizecon.read_parquet()to load data from external sources.\n - Boundary markers: The instructions do not define specific boundary markers or provide explicit directions to the agent to ignore or isolate potentially malicious content embedded within the data.\n
- Capability inventory: The skill allows for file system operations, including reading Parquet files, writing to Parquet and CSV formats, and generating visualization image files.\n
- Sanitization: There is no evidence of explicit content validation or sanitization for the data ingested from the Parquet files before it is processed by the analysis logic.\n- [EXTERNAL_DOWNLOADS]: The skill instructions include steps to install the Ibis framework (with DuckDB support) and Matplotlib from standard Python package registries to enable its data analysis and visualization capabilities.
Audit Metadata