vetty

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from npm. This is the official command-line interface for the Membrane platform, which is the author of the skill. This is a standard procedure for using the platform's services.
  • [COMMAND_EXECUTION]: The skill uses various membrane CLI commands to manage authentication, list connections, and execute actions. These commands are localized to the vendor's platform and do not perform arbitrary or malicious shell execution.
  • [CREDENTIALS_UNSAFE]: The skill explicitly instructs the user not to share API keys or tokens, instead using a server-side connection mechanism that manages credentials securely without exposing them to the local environment.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 09:39 PM