sheetdb

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the NPM registry. This is the official command-line interface for the vendor's platform and is necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: The instructions involve running several shell commands using the membrane CLI. These commands are used for authenticating the user, connecting to the SheetDB service, and executing data-related actions.
  • [DATA_EXFILTRATION]: The skill is designed to move data between the agent and Google Sheets. It mitigates credential theft risks by instructing the agent to never request or store raw API keys, instead using managed connections where the authentication lifecycle is handled server-side by Membrane.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 08:41 PM
Security Audit — agent-trust-hub — sheetdb