cloudbase
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured guidance for integrating Tencent CloudBase features such as authentication, database management, and cloud functions. It utilizes official SDKs and MCP tools for all operations.
- [EXTERNAL_DOWNLOADS]: The skill recommends installing official packages from NPM (e.g.,
@cloudbase/js-sdk,@cloudbase/node-sdk) and usingnpxto run verified tools like@cloudbase/cloudbase-mcpandmcporter. These are standard development practices for the CloudBase ecosystem. - [COMMAND_EXECUTION]: Instructions involve calling authorized MCP tools (e.g.,
executeWriteSQL,manageCloudRun,callCloudApi) to perform management tasks. These commands are executed within the agent's scoped tool environment for development purposes. - [CREDENTIALS_UNSAFE]: No hardcoded secrets were found. The skill explicitly instructs developers to avoid hardcoding Secret IDs or Keys and recommends using environment variables or device-code authentication via the
authtool. - [PROMPT_INJECTION]: The skill contains no instructions designed to bypass safety filters or override the agent's core behavior. It focuses on implementing standard software engineering workflows (e.g., requirement analysis and technical design).
Audit Metadata