python-visuals
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill consumes untrusted data via the
datasetpandas DataFrame, which is automatically injected into the script context by the Power BI environment. - Ingestion points: The
datasetvariable is referenced throughoutSKILL.mdand all files in theexamples/andreferences/directories as the primary data source. - Boundary markers: None. The instructions and scripts do not implement specific delimiters or instructions to treat data content as untrusted.
- Capability inventory: The skill utilizes
matplotlib,seaborn, andpandasfor data manipulation and image rendering. While Power BI Service restricts network access, the desktop environment allows unrestricted package usage. - Sanitization: None. Data values are used directly in visual labels, chart titles, and text annotations without prior validation or escaping.
Audit Metadata