azure-virtual-desktop-manager
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides legitimate instructions for designing, deploying, and managing Azure Virtual Desktop environments using infrastructure-as-code and automation scripts.
- [INDIRECT_PROMPT_INJECTION]: The skill is intended to process external configuration data, such as Bicep templates, ARM templates, Terraform files, and Azure Policy definitions. While this introduces a theoretical surface for indirect prompt injection, the skill acts as a guide for the user and does not directly execute untrusted external inputs in a high-risk manner.
- Ingestion points: External configuration files (.bicep, .tf, .json), scripts (.ps1, .sh), and monitoring data (.kql, .csv) provided by the user.
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: Generation of PowerShell commands, Azure CLI commands, and infrastructure-as-code snippets.
- Sanitization: No specific sanitization or validation logic for external content is mentioned.
- [SAFE]: All referenced resources, including the GitHub repository link and the platform target, are consistent with the identified author and platform.
Audit Metadata