exploratory-data-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's workflow and code examples are consistent with legitimate data analysis practices. It utilizes standard Python packages for data manipulation and visualization.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted tabular data from CSV files. While this provides an attack surface for indirect prompt injection, the data is used for profiling and statistical analysis rather than being interpreted as instructions or passed into sensitive functions, which minimizes the risk.
Audit Metadata