kickbox
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/clipackage via NPM. This is an official tool from the skill's author (Membrane) and is required for the integration to function. - [COMMAND_EXECUTION]: Uses shell commands to interact with the
membraneCLI for managing connections and executing actions. This is the primary mechanism of the skill and does not include arbitrary or suspicious command patterns. - [CREDENTIALS_UNSAFE]: The skill explicitly follows best practices for credential management by instructing the agent to never ask the user for API keys, instead relying on the Membrane platform's server-side authentication flow.
Audit Metadata