refreshing-semantic-model

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the fab CLI and a Python wrapper script (scripts/refresh_model.py) to manage semantic model refreshes.
  • Commands are executed using subprocess.run with list-based arguments rather than shell strings, which effectively prevents shell injection vulnerabilities.
  • The logic is restricted to Power BI API interactions (triggering refreshes, checking status, and running validation queries).
  • [EXTERNAL_DOWNLOADS]: The skill communicates with the Power BI REST API through the fab CLI tool.
  • Interactions are limited to well-known service endpoints for Power BI management.
  • No external executable code or scripts are downloaded from untrusted sources.
  • [SAFE]: A thorough analysis of instructions and scripts found no malicious behavior.
  • No hardcoded credentials or attempts to access sensitive system files (e.g., SSH keys, environment variables) were found.
  • The instructions provide standard administrative workflows for managing Power BI datasets.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 05:04 PM
Security Audit — agent-trust-hub — refreshing-semantic-model