business-analyst
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, such as customer feedback and market datasets, creating a surface for indirect prompt injection. * Ingestion points: Dataset analysis commands for churn, sales funnels, and market research are defined in SKILL.md. * Boundary markers: The instructions lack delimiters or 'ignore embedded instructions' warnings for processed data. * Capability inventory: The skill utilizes Python, SQL, and R execution capabilities as described in SKILL.md and references/kpi-dashboard-design.md. * Sanitization: There are no provisions for filtering or escaping input data before it is interpreted by the agent.
- [DYNAMIC_EXECUTION]: The skill provides templates and snippets for SQL and Python (Streamlit/Plotly) to be executed by the agent at runtime. * Evidence: Code blocks in references/kpi-dashboard-design.md contain SQL for KPI calculation and Python for dashboard generation.
Audit Metadata