The Agent Skills Directory

[SAFE]: The skill is a standard integration guide that uses official vendor resources. No malicious behavior or security policy violations were found.
[EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package and running tools via npx. As these are official resources from the skill's author (membranedev), they are considered safe vendor components.
[COMMAND_EXECUTION]: Provides CLI commands for authentication and data management. These operations are performed through the Membrane platform, which handles credentials securely server-side, adhering to best practices for secret management.
[CREDENTIALS_UNSAFE]: The instructions explicitly advise against asking users for API keys or tokens, directing the agent to use Membrane's connection system instead. This prevents accidental exposure of sensitive credentials.

voiceflow