The Agent Skills Directory

[SAFE]: The skill acts as a configuration and best practices guide for Azure MCP integration. All external resources, including documentation and GitHub repositories, belong to the 'microsoft' organization, which is a recognized trusted vendor. All authentication methods described, such as Azure CLI and environment variables for service principals, align with standard security best practices for cloud management.
[INDIRECT_PROMPT_INJECTION]: The skill documents tools that ingest data from external Azure services, creating a potential surface for processing untrusted content. However, as a high-level instructional guide for official Microsoft tools, it does not implement executable logic or unsafe interpolation.
Ingestion points: monitor_logs_query, cosmosdb_query (references external database and log data).
Boundary markers: None specified in the reference documentation.
Capability inventory: Azure MCP tools for listing, getting, creating, and querying resources across 40+ services.
Sanitization: Not addressed in this high-level best practices guide.

azure-usage