smartsheet

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli Node.js package. This is a legitimate tool provided by the vendor (Membrane) to facilitate the integration.
  • [COMMAND_EXECUTION]: The skill executes several CLI commands (membrane login, membrane action, membrane request) to manage authentication and interact with the Smartsheet API.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests and processes data from external Smartsheet resources. \n
  • Ingestion points: Data from Smartsheet rows, cells, and sheets retrieved via CLI actions. \n
  • Boundary markers: Absent. \n
  • Capability inventory: The skill can modify or delete data using update-rows and delete-sheet actions, and perform arbitrary HTTP requests via the membrane request proxy. \n
  • Sanitization: No explicit sanitization or filtering of external content is described in the prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 08:59 AM