ml-azureml-adf-automation

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior detected. The skill provides legitimate automation guidelines for Microsoft Azure services.
  • [EXTERNAL_DOWNLOADS]: Recommends installing standard Azure SDK packages (azure-ai-ml, azure-identity) and a library constraint (marshmallow) via pip.
  • [COMMAND_EXECUTION]: Provides scripts using Azure CLI and PowerShell for resource management, which is consistent with the skill's purpose.
  • [DATA_EXFILTRATION]: Makes a request to https://api.ipify.org to obtain the agent's public IP address for configuring temporary storage firewall rules. This is a standard practice for secure CI access to private storage.
  • [CREDENTIALS_UNSAFE]: Correctly utilizes AzureCliCredential and Managed Service Identity (MSI) for authentication, avoiding the use of hardcoded credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:39 AM
Security Audit — agent-trust-hub — ml-azureml-adf-automation