microsoft-foundry

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • Source Code Analysis Surface: The skill includes functionality to scan user source code for environment variables and configuration knobs (e.g., in the deploy and faos-optimize sub-skills). This is a necessary part of the deployment and optimization workflow, though it represents a surface where the agent processes external data.
  • Trusted External Downloads: The skill fetches sample code and infrastructure templates from official Microsoft GitHub repositories (microsoft-foundry/foundry-samples and Azure-Samples/azd-ai-starter-basic). These operations are documented and target well-known, trusted organizations.
  • Automated Command Execution: This skill makes extensive use of the Azure CLI (az) and the Azure Developer CLI (azd) to manage cloud resources. These commands are executed to perform administrative tasks such as resource group creation, role assignments, and model deployments as requested by the user.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 10:09 PM