bkend-quickstart
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as documentation and a configuration guide for bkend.ai. All URLs (api.bkend.ai) and packages (@bkend/client, @bkend/mcp-server) are consistent with the stated purpose of the skill.
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the
@bkend/clientpackage via npm and utilize the@bkend/mcp-servervia npx. These are standard dependency management practices for the supported service. - [REMOTE_CODE_EXECUTION]: The MCP configuration utilizes
npx @bkend/mcp-server, which is a legitimate use case for connecting a Model Context Protocol server to the agent's environment. - [CREDENTIALS_UNSAFE]: The skill correctly advises using environment variables (
.env.local) for project identifiers and API URLs, following security best practices for frontend applications. It explicitly directs users to a separate skill ($bkend-auth) for sensitive authentication details.
Audit Metadata