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

azure-cost

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • Standard Command Execution: The skill provides instructions for using official Azure CLI (az) and Kubernetes CLI (kubectl) commands to retrieve metrics, list resources, and query cost data. These operations are standard for cloud administration and are restricted to the user's existing permissions.
  • Secure Authentication Patterns: Documentation within the skill explicitly recommends the use of Managed Identities and the Azure Identity SDKs for production environments. It provides clear guidance on avoiding hardcoded credentials and utilizing platform-managed authentication, which aligns with industry security standards.
  • Controlled Network Operations: All network requests described in the workflow are directed to official Azure management endpoints (e.g., management.azure.com). The skill correctly instructs the agent to include mandatory headers like ClientType: GitHubCopilotForAzure for proper request identification.
  • Data Processing and Ingestion: The skill processes structured JSON data from Azure APIs to generate cost reports. While it ingests external data from the Azure platform, this data is restricted to the user's own cloud tenant, and the skill includes logic for handling service-specific responses and error codes like rate limiting (HTTP 429).
  • User Oversight for Destructive Actions: The instructions emphasize obtaining explicit user approval before executing any destructive operations, such as deleting orphaned resources or modifying resource tiers, ensuring human-in-the-loop control.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:51 PM
Security Audit — agent-trust-hub — azure-cost