The Agent Skills Directory

[SAFE]: The skill follows security best practices by explicitly restricting its scope to read-only operations and avoiding destructive actions such as configuration changes, restarts, or failovers.
[COMMAND_EXECUTION]: The skill instructs the agent to use standard Azure CLI (az) commands (e.g., az vm get-instance-view, az aks show) for diagnostic purposes. These operations are scoped to fetching resource states and activity logs, which is consistent with the skill's troubleshooting intent.
[DATA_EXFILTRATION]: No unauthorized network requests or data exfiltration patterns were detected. Analysis results are directed to local workspace directories (Troubleshooting/ or Answer/) for report generation.
[INDIRECT_PROMPT_INJECTION]: Although the skill processes external data like Azure activity logs and resource health events, it defines a structured analytical workflow that focuses on status interpretation and fact collection, minimizing the risk of executing instructions embedded in log data.

azure-troubleshooting