fabriciq
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- Indirect Prompt Injection Surface: The skill is designed to retrieve and strictly adhere to 'CustomInstructions' and 'VerifiedAnswers' contained within external Power BI semantic models via the 'GetSemanticModelSchema' tool in 'SKILL.md'. Because the agent treats these as high-priority rules for generating DAX queries, a maliciously configured model could potentially influence the agent's logic or data retrieval behavior. This represents an indirect prompt injection surface where the agent's output is shaped by data it ingests from external reports.
- Query Execution Capability: The skill utilizes the 'ExecuteQuery' tool in 'SKILL.md' to run DAX statements against business datasets. While this is the intended functionality for data analysis, it involves the generation and execution of queries based on user input and model schema, which warrants standard data access auditing.
- External Resource Integration: The skill manifest 'apm.yml' references an external MCP endpoint at 'https://api.fabric.microsoft.com/v1/mcp/fabricaihub/integrations/m365'. This endpoint is used to provide the core FabricIQ functionality and is hosted on a recognized domain associated with the skill's author.
Audit Metadata