svix

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the public NPM registry, which is the standard tool for the author's platform.
  • [COMMAND_EXECUTION]: Uses the membrane command-line interface to search for connectors, manage connections, and execute actions on the Svix platform.
  • [CREDENTIALS_UNSAFE]: Follows security best practices by explicitly directing the agent not to ask for or store user API keys, instead utilizing the platform's native secure authentication lifecycle.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 05:38 PM
Security Audit — agent-trust-hub — svix