azure-cost-optimization
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS] (LOW): The skill references standard package installations (
dotnet add package Azure.ResourceManager.Redis). These are sourced from trusted official Microsoft registries. - [INDIRECT_PROMPT_INJECTION] (LOW): The skill processes untrusted data from Azure resource metadata (names, tags) to generate optimization reports.
- Ingestion points: Data enters through
az graph queryandaz redis list(referenced inazure-resource-graph.mdandazure-redis.md). - Boundary markers: No explicit delimiters or instruction-bypass warnings are defined for the report templates.
- Capability inventory: The skill identifies resources for modification or deletion via
az redis deleteandaz redis update(referenced intemplates/redis-detailed-cache-analysis.md). - Sanitization: No explicit sanitization of resource tags or names is mentioned before they are interpolated into the report templates.
- [CREDENTIALS_UNSAFE] (SAFE): Analysis of the SDK reference (
azure-resource-manager-redis-dotnet.md) confirms a strong security posture, explicitly forbidding hardcoded keys and mandating the use ofDefaultAzureCredential.
Audit Metadata