build-mcp-use-agent
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides extensive documentation and runnable examples for building TypeScript agents. It includes robust security guidance, such as anti-patterns that warn against hardcoding secrets and instructions for proper resource cleanup using
try/finallyblocks and signal handlers. - [EXTERNAL_DOWNLOADS]: The skill references established packages and tools within the Model Context Protocol ecosystem, such as
@modelcontextprotocol/server-filesystemand@playwright/mcp. These are standard, well-known resources for the library's intended use case. - [COMMAND_EXECUTION]: Included diagnostic and scaffolding scripts (e.g.,
diagnose-agent-stuck.sh) perform read-only checks on the local environment or generate project templates. These scripts are intended for developer use and do not execute untrusted remote code or perform dangerous system modifications. - [CREDENTIALS_UNSAFE]: The skill maintains a high standard for credential safety. It explicitly instructs users to store sensitive information like API keys in
.envfiles and avoid committing them to source control, which aligns with industry security standards.
Audit Metadata