Power BI Paginated Reports

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute TypeScript and PowerShell automation scripts provided in the documentation for managing report lifecycles and performing filesystem operations.
  • [PROMPT_INJECTION]: The skill processes external RDL XML files and Power BI API data, creating a surface for indirect prompt injection. Ingestion points: Reading .rdl files via the Read tool and processing REST API responses from api.powerbi.com. Boundary markers: No delimiters or isolation instructions are present in the provided examples when processing external data. Capability inventory: The skill allows for script execution via Bash and network communication via axios. Sanitization: No validation or sanitization logic is implemented for the data ingested from external sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 06:10 AM
Security Audit — agent-trust-hub — Power BI Paginated Reports