sqldw-cli

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFE
Full Analysis
  • Structured SQL Execution: The skill utilizes a dedicated MCP tool (fabric-sqlendpoint-execute_query) to interact with Fabric data warehouses and SQL endpoints. This method is preferred over generic shell-based SQL clients, reducing the risk of shell injection.
  • Vendor-Owned Infrastructure: Network operations are directed towards api.fabric.microsoft.com, which is the official endpoint for the service. All discovery and management tasks are conducted through standard vendor APIs.
  • Comprehensive Documentation: The skill includes detailed reference files for different operation modes (authoring, consumption, operations), ensuring the agent has necessary context to generate valid and safe T-SQL commands.
  • Least Privilege and RBAC: The instructions correctly reference necessary Azure RBAC roles (such as Contributor for Query Insights or Storage Blob Data Reader for ingestion), encouraging a secure permission model.
  • Standard Data Ingestion Patterns: T-SQL commands for data ingestion (COPY INTO, OPENROWSET) use placeholder URLs for Azure Data Lake Storage (ADLS) Gen2, representing standard functionality for the Fabric platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 01:44 PM
Security Audit — agent-trust-hub — sqldw-cli