azure-kusto
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from external sources via the
kusto_querytool and Azure CLI fallback commands. - Ingestion points: Data retrieved from Azure Data Explorer tables, logs, and telemetry streams.
- Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the retrieved data.
- Capability inventory: The skill has capabilities to execute KQL queries and run Azure CLI commands (
az rest,az kusto). - Sanitization: There is no mention of sanitizing or escaping the content returned from the database before the agent processes it.
- [COMMAND_EXECUTION]: The skill explicitly provides a fallback strategy using Azure CLI commands (
az kusto cluster list,az kusto database list,az rest). While these are standard management tools, they involve the agent executing shell commands to interact with cloud infrastructure and retrieve data.
Audit Metadata