azure-well-architected
Pass
Audited by Gen Agent Trust Hub on Mar 8, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references numerous URLs from the official documentation domain 'learn.microsoft.com'. These references are used to fetch design guidelines, checklists, and best practices for Azure workloads.
- [COMMAND_EXECUTION]: No unauthorized or dangerous system commands, shell scripts, or administrative operations were detected within the skill's instructions.
- [PROMPT_INJECTION]: The instructions provided to the agent are operational, focusing on efficient file reading and tool selection. There are no attempts to override safety filters, extract system prompts, or induce unrestricted behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external documentation content via 'mcp_microsoftdocs:microsoft_docs_fetch'. While this introduces a data ingestion surface, the sources are limited to official Microsoft documentation, which is a well-known and trusted service.
- [DATA_EXPOSURE]: There is no evidence of hardcoded credentials, sensitive file path access, or unauthorized data exfiltration patterns.
Audit Metadata