programmatic-eda
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides tools for local data analysis. All operations (loading, profiling, and reporting) are conducted locally using standard data science libraries (pandas, numpy). No evidence of credential theft, data exfiltration, or unauthorized command execution was found.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external files (CSV, Parquet, Excel), which presents a standard attack surface for indirect prompt injection.
- Ingestion points: Dataset files loaded via pandas in
scripts/data_overview.py,scripts/null_profiler.py,scripts/outlier_detector.py,scripts/distribution_summary.py, andscripts/correlation_explorer.py. - Boundary markers: None.
- Capability inventory: Data processing and local reporting (printing to console and saving CSV files). The skill lacks network access or dynamic code execution capabilities, significantly limiting the impact of any potential injection.
- Sanitization: Standard pandas parsing.
Audit Metadata