microsoft-excel

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill leverages the Membrane CLI (membrane) to perform all interactions with Microsoft Excel. This includes logging in, managing connections, and executing specific spreadsheet actions. This approach centralizes security and authentication logic.\n- [EXTERNAL_DOWNLOADS]: The instructions require the installation of the @membranehq/cli tool from the official NPM registry. This is a trusted dependency authored by the skill's developer and is standard for managing Membrane-based integrations.\n- [PROMPT_INJECTION]: The skill processes data from Excel workbooks, which constitutes an ingestion surface for potentially untrusted content.\n
  • Ingestion points: Spreadsheet data enters the agent context through actions such as get-cell, get-range, and list-table-rows.\n
  • Boundary markers: No explicit delimiters or boundary markers are mentioned in the skill instructions to frame or isolate spreadsheet content.\n
  • Capability inventory: The skill possesses capabilities to execute CLI commands and make network requests via the membrane request and membrane action run commands.\n
  • Sanitization: The skill documentation does not describe specific sanitization or validation processes for data extracted from Excel before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 09:51 AM