azure-architecture-autopilot
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
powershelltool to execute Azure CLI (az) commands for scanning existing resources, validating Bicep templates, and performing deployments. These operations are within the stated scope of the skill and follow user-approved workflows. - [REMOTE_CODE_EXECUTION]: The
scripts/cli.pyscript dynamically generates a Node.js script and executes it viasubprocess.runto utilizepuppeteerfor converting HTML diagrams to PNG images. This is a legitimate functional requirement for the skill's visualization and export capabilities. - [EXTERNAL_DOWNLOADS]: The skill utilizes the
web_fetchtool to retrieve service specifications, API versions, and model availability directly from official Microsoft documentation atlearn.microsoft.comandazure.microsoft.com. These are trusted well-known sources and the findings are neutral. - [CREDENTIALS_UNSAFE]: The skill instructions explicitly forbid asking for or storing secrets in plaintext. It mandates the use of Azure Key Vault and
@secure()parameters for sensitive data, which is a significant security best practice.
Audit Metadata