azure-enterprise-infra-planner

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill utilizes local CLI tools such as the Azure CLI (az) and Terraform to manage and deploy cloud resources. These operations are core to the skill's purpose and are protected by validation steps and a mandatory user confirmation gate for any destructive or deployment actions.
  • Indirect Prompt Injection: The skill is designed to process existing infrastructure definitions, documentation, and user requirements. While ingesting external content presents a potential surface for indirect prompt injection, the skill mitigates this through a multi-phase verification pipeline that includes automated security checks and manual user approval of the final plan.
  • Automated Security Validation: The workflow incorporates checkov to perform static analysis on generated Infrastructure-as-Code (IaC) files. This ensures that potential security misconfigurations are identified and addressed prior to deployment.
  • Privileged Operations: The skill supports subscription-level infrastructure planning and deployment. The potential risks associated with high-privilege access are managed by a gated pipeline where each phase must pass verification, and the final execution requires explicit, risk-acknowledged confirmation from the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 06:30 PM