unlaunch
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
@membranehq/clipackage globally using npm to enable interaction with the Membrane environment. - [COMMAND_EXECUTION]: Orchestrates various CLI commands (e.g.,
membrane login,membrane connect,membrane action run) to automate workflows and manage remote configurations on Unlaunch. - [PROMPT_INJECTION]: The skill uses instructional language to guide the agent but does not contain patterns attempting to bypass safety filters or override system constraints.
- [CREDENTIALS_UNSAFE]: No hardcoded secrets or API keys are present. The skill explicitly advises using Membrane connections to handle authentication server-side, avoiding local secret storage.
Audit Metadata