tmdl
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing documentation, syntax rules, and a complete real-world example model for Tabular Model Definition Language (TMDL) authoring. It does not contain executable scripts or binary payloads.
- [SAFE]: No evidence of hardcoded credentials or sensitive data access was found. Parameters like 'SqlEndpoint' in 'expressions.tmdl' use placeholder values and are standard for semantic model configurations.
- [SAFE]: The skill correctly instructs the agent to use standard tools like Tabular Editor or Microsoft Documentation for specific tasks, which are well-known and trusted within the Power BI ecosystem.
- [SAFE]: All DAX and M expressions provided in the examples follow standard Power BI patterns and do not contain any obfuscated or malicious logic.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and edit configuration files (.tmdl, .bim). While processing external data is a theoretical vector for indirect prompt injection, the risk is negligible here as the instructions focus on structured data authoring and follow best practices for model validation.
Audit Metadata