azure-kusto
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted telemetry and log data from Azure Data Explorer tables. Malicious instructions embedded in these logs could potentially influence the agent's logic. * Ingestion points: Results from kusto_query and az rest. * Boundary markers: Absent; no specific instructions to treat query results as untrusted data. * Capability inventory: Resource listing and KQL query execution. * Sanitization: Absent.
- [Command Execution] (SAFE): The skill includes a fallback strategy using Azure CLI (az kusto, az rest) to interact with the Azure API. While this involves shell-level execution, it is the intended primary function of the skill for cloud resource management and targets trusted Azure endpoints.
Audit Metadata