azure-prepare

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains authoritative instructions directing the agent to prioritize its provided guidance over prior training. This is a standard grounding technique used to ensure the agent follows the specific, verified Azure deployment recipes defined within the skill.
  • [EXTERNAL_DOWNLOADS]: The documentation includes instructions for installing the Azure Developer CLI (azd) from Microsoft's official aka.ms domain. This is an industry-standard method for installing official tooling and originates from a trusted organization.
  • [DATA_EXFILTRATION]: The skill performs scans of the local workspace to identify project dependencies and technology stacks. This information is used solely to generate a deployment plan and infrastructure configuration. The workflow includes a mandatory step to present this plan to the user for review and approval.
  • [COMMAND_EXECUTION]: The recipes provide templates for Azure CLI, Terraform, and Docker commands. These commands are necessary for the skill's primary function of infrastructure preparation and application containerization and are designed for use within the user's authenticated environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:50 PM
Security Audit — agent-trust-hub — azure-prepare