microsoft-power-bi
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the Membrane CLI tool (@membranehq/cli) from the NPM registry to provide the necessary environment for Power BI interactions. This is a vendor-provided tool from the Membrane ecosystem.
- [COMMAND_EXECUTION]: Shell commands are used to manage authentication and execute Power BI actions. This includes 'membrane login' for session establishment and 'membrane request' for direct API interaction through the platform proxy.
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by retrieving potentially untrusted data from external Power BI resources that could influence agent logic.
- Ingestion points: Data fetched via report listing, dataset details, workspace users, and raw proxy requests as defined in SKILL.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded content are present in the skill instructions.
- Capability inventory: The skill possesses resource management capabilities including 'create-workspace', 'delete-report', 'delete-dataset', and arbitrary HTTP proxying to the Power BI API as seen in SKILL.md.
- Sanitization: No data validation or sanitization routines are implemented for external API responses before they are processed by the agent.
Audit Metadata