skills/microsoft/skills/azure-kusto/Gen Agent Trust Hub

azure-kusto

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • Command Execution via Azure CLI: The skill includes instructions to use the standard az CLI as a fallback mechanism. This is a common pattern in Azure-focused skills to ensure operational continuity when specialized tools are unavailable.
  • Indirect Prompt Injection Surface: The skill is designed to ingest and process data from external Kusto databases. While this is the primary purpose of the skill, it creates a surface where external content is brought into the agent's context.
  • Ingestion points: Data is retrieved via kusto_query tool and az rest commands.
  • Capability inventory: The agent has the ability to execute KQL queries and run shell commands through the Azure CLI.
  • Boundary markers: The skill does not explicitly define delimiters for query results, which is typical for data analysis skills.
  • Sanitization: Standard handling of query results is expected; no custom sanitization logic is implemented in the prompt itself.
  • Trusted Resource Usage: All external references, including URLs (kusto.windows.net) and tools, are official Microsoft Azure resources, aligning with the skill's authorship.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 04:31 PM
Security Audit — agent-trust-hub — azure-kusto