azure-openai-service
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI (
@membranehq/cli) via npm. This package is the official interface for the Membrane platform and is a legitimate dependency provided by the vendor. - [COMMAND_EXECUTION]: The skill documentation provides shell commands using the
membraneCLI to authenticate, manage Azure OpenAI connections, and execute AI actions. These commands are necessary for the skill's functionality and do not exhibit malicious intent or excessive privileges. - [CREDENTIALS_UNSAFE]: The skill implements secure credential handling by advising users to create platform-managed connections. This prevents the exposure of raw Azure API keys within the agent's environment or logs, aligning with security best practices.
Audit Metadata