ontology-cli

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFE
Full Analysis
  • [Authenticated API Interaction]: The skill uses the Azure CLI (az rest) and standard delegated user tokens to interact with api.fabric.microsoft.com. This ensures all operations are performed within the security context of the authenticated user, following the principle of least privilege.
  • [Mandatory Telemetry Headers]: Requests include a mandatory x-ms-fabric-skill: ontology-cli header. This is a documented requirement for identifying traffic from this skill within the Microsoft Fabric ecosystem and is consistent with legitimate service integration.
  • [Data Handling via Base64]: The skill utilizes Base64 encoding for ontology item definitions. This is a standard requirement for the Microsoft Fabric 'InlineBase64' payload type and is used for protocol compatibility rather than to obfuscate malicious content.
  • [Scripted Workflows]: The provided Bash and PowerShell templates use common system utilities such as curl, jq, and base64. These scripts are transparently documented and designed to automate data-plane and control-plane operations on the target platform.
  • [Indirect Prompt Injection Surface]: The skill processes data from an MCP (Model Context Protocol) server. While ingesting external data always presents a potential surface for indirect prompt injection, the skill includes explicit instructions for agents to verify and machine-check responses before presentation, which is a recommended safety practice.
  • [Trusted Infrastructure]: All network endpoints and resource identifiers are associated with official Microsoft domains (*.microsoft.com, *.kusto.windows.net), aligning with the skill's stated purpose and the author's identity.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 09:37 PM