azure-copilot
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches documentation content from official Microsoft domains (learn.microsoft.com) to provide the agent with current technical information. These operations use source tracking parameters (e.g., from=learn-agent-skill) for documentation telemetry.
- [COMMAND_EXECUTION]: Provides templates and guidance for generating Azure CLI, PowerShell, and Infrastructure-as-Code (Terraform/Bicep) scripts. The skill assists in authoring these scripts but does not contain instructions to execute them automatically or bypass user review.
- [PROMPT_INJECTION]: Includes instructional guidance for the agent (e.g., 'IMPORTANT for Agent') regarding how to index the skill and handle stale metadata. These instructions are standard for operationalizing the skill and do not attempt to bypass safety filters or override core agent behavior.
Audit Metadata