google-cloud-translate
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill follows security best practices by utilizing the official Membrane CLI (@membranehq/cli) for managing authentication and connections, which prevents the need for hardcoded credentials.
- [EXTERNAL_DOWNLOADS]: The instructions include installing the Membrane CLI from npm, which is a standard distribution method for this vendor's official tooling.
- [COMMAND_EXECUTION]: The skill utilizes command-line interactions through the Membrane CLI to perform translation actions and manage connections securely.
- [SAFE]: The skill has an indirect prompt injection surface as it processes text for translation. Ingestion points: translation text (SKILL.md). Boundary markers: absent. Capability inventory: network and connection management via membrane CLI. Sanitization: absent. The risk is considered safe as it is the core functionality.
Audit Metadata