powerbi-modeling

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect prompt injection surface identified in the model management workflow.
  • Ingestion points: The skill ingests data from external Power BI semantic models (e.g., table names, column definitions, and measure descriptions) as seen in the 'Practical Workflow' of SKILL.md and the audit logic in scripts/powerbi-model-audit.py.
  • Boundary markers: No specific boundary markers or instructions to ignore instructions within model metadata were identified in the workflow or reference documentation.
  • Capability inventory: The skill leverages powerful model-modification tools through the Power BI MCP server, including table_operations, measure_operations, relationship_operations, and security_role_operations (documented in examples/model-examples.md).
  • Sanitization: There is no evidence of sanitization or validation of the ingested metadata before it is processed or used to generate model updates.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 11:59 AM
Security Audit — agent-trust-hub — powerbi-modeling