azure-virtual-desktop-manager
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of high-level instructions and best practice recommendations for Azure Virtual Desktop administration. It does not contain executable code, scripts, or automated triggers.
- [PROMPT_INJECTION]: The content is strictly directive and focuses on professional tasks. There are no attempts to bypass safety filters, extract system prompts, or override agent instructions.
- [DATA_EXFILTRATION]: No network operations or requests to external domains are initiated. The skill references the author's official GitHub repository and the Tasking.tech platform, both of which are consistent with the skill's metadata.
- [COMMAND_EXECUTION]: The skill mentions providing PowerShell and Azure CLI commands to users as part of runbooks, but it does not instruct the agent to execute these commands autonomously or perform unauthorized system modifications.
- [REMOTE_CODE_EXECUTION]: There are no remote script downloads or dynamic code execution patterns. All dependencies mentioned are standard Azure-related file formats for infrastructure-as-code and configuration.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process Azure configuration files and logs (Ingestion points: .bicep, .tf, .json, .kql files), it lacks automated execution capabilities that would make this surface exploitable. No specific boundary markers or sanitization logic are defined, which is standard for instructional content.
Audit Metadata