microsoft-excel

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the Membrane CLI (@membranehq/cli) from the npm registry, which is the official tool provided by the vendor.
  • [COMMAND_EXECUTION]: Shell commands are utilized via the membrane CLI to perform authentication, connection management, and execution of Excel-related actions.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Microsoft Excel workbooks, creating a surface for indirect prompt injection if the workbook content contains malicious instructions.
  • Ingestion points: Data is retrieved from cells, tables, and ranges (e.g., get-cell, list-table-rows, get-range) as specified in SKILL.md.
  • Boundary markers: The skill does not define explicit delimiters or instructions to ignore commands within the ingested spreadsheet data.
  • Capability inventory: The agent has the ability to run shell commands, write to the filesystem, and perform network requests through the Membrane proxy across all CLI-driven interactions.
  • Sanitization: There is no evidence of data sanitization or validation performed on the content retrieved from Excel before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 07:09 AM