azure-usage
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill defines tools for querying external Azure data sources like Log Analytics and Cosmos DB, which presents a surface for indirect prompt injection. However, this is consistent with the skill's primary purpose of resource management. Evidence: 1. Ingestion points: monitor_logs_query, cosmosdb_query, keyvault_secrets_get; 2. Boundary markers: None specified in documentation; 3. Capability inventory: Comprehensive Azure resource management (List, Get, Create, Query); 4. Sanitization: Not specified in documentation.
- [Unverifiable Dependencies] (SAFE): All external links point to microsoft.com or official Microsoft GitHub repositories, which are identified as trusted sources under the [TRUST-SCOPE-RULE].
Audit Metadata