semantic-model-consumption

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • Structured Metadata Discovery: The skill implements a progressive discovery approach, using DAX functions like INFO.VIEW.TABLES and INFO.VIEW.COLUMNS to inspect model schemas. This allows for focused data retrieval and is a standard practice for semantic model exploration.
  • Governed Tool Integration: The instructions prioritize the use of official MCP tools (ExecuteQuery, DiscoverArtifacts) over direct shell commands. This pattern ensures that interactions with the Fabric service are mediated by specialized interfaces designed for this purpose.
  • Read-Only Operational Guardrails: The skill is explicitly scoped for read-only operations, such as metadata inspection and analytical DAX queries. It includes clear directives to avoid model-change operations, which maintains the integrity of the target environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 02:45 PM
Security Audit — agent-trust-hub — semantic-model-consumption