azure-kusto
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Dynamic Execution] (LOW): The skill defines a fallback strategy using Azure CLI commands that involves dynamic string interpolation into shell commands. Evidence: SKILL.md contains 'az rest' and 'az kusto' command patterns. Risk: Potential shell injection if the agent fails to properly escape inputs like KQL queries or database names. Severity is lowered because this is restricted to its primary function of cloud management.
- [Indirect Prompt Injection] (LOW): The skill has a surface for Indirect Prompt Injection (Category 8). 1. Ingestion points: Logs, telemetry, and event data retrieved via 'kusto_query' or 'az rest'. 2. Boundary markers: Absent; no delimiters are provided to isolate external data from instructions. 3. Capability inventory: Includes 'kusto_query' and shell command execution ('az'). 4. Sanitization: Absent; no specific instructions for validating or escaping external data before processing are included.
Audit Metadata