one-ai
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the installation and use of the '@membranehq/cli' global NPM package to perform operations such as managing chat sessions, workspaces, and actions.
- [SAFE]: The instructions explicitly recommend using Membrane connections for authentication, which prevents the exfiltration or exposure of sensitive API keys or tokens.
- [PROMPT_INJECTION]: The skill processes natural language input via the '--intent' parameter in action searching and the description field in action creation. While this creates a surface for indirect prompt injection, it is a core feature of the vendor's tool and depends on the platform's internal sanitization.
- [SAFE]: All referenced resources, including the NPM package, homepage, and repository, originate from the verified vendor 'membranedev'.
Audit Metadata