fabriciq-ontology-cli

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [Data Processing Surface]: The skill ingests ontology definitions and source data from Microsoft Fabric to provide grounding context and generate queries. While processing external content carries an inherent risk of indirect prompt injection, the skill includes logic for remapping identifiers and sanitizing values, and the behavior is consistent with its intended purpose as a data exploration tool.
  • [Command Generation and Execution]: The skill generates shell commands using az rest, curl, and specific Fabric CLI tools to interact with official Microsoft endpoints. This is standard functionality for an infrastructure management skill and leverages the environment's authenticated context.
  • [Use of Trusted Service Endpoints]: All network operations and data references target microsoft.com subdomains (such as api.fabric.microsoft.com and onelake.dfs.fabric.microsoft.com), which are well-known service endpoints for the target platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 01:44 PM
Security Audit — agent-trust-hub — fabriciq-ontology-cli