kpi-dashboard
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a clear, benign workflow for generating KPI dashboards from user-provided operating data. It does not attempt to bypass safety filters or perform unauthorized actions.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied operating data (sales, finance, etc.), which represents a potential attack surface for indirect prompt injection. However, the instructions focus on structural data transformation into Excel formulas, and the impact is mitigated by standard platform tool constraints. Evidence:
- Ingestion points: Operating data provided by the user (SKILL.md)
- Boundary markers: None specified
- Capability inventory: Uses spreadsheet tools to create workbooks (SKILL.md)
- Sanitization: None specified
Audit Metadata