build-agents
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFE
Full Analysis
- Standard Development Workflows: The skill utilizes standard package management commands (e.g.,
npx eve@latest init) to scaffold projects. These are common developer patterns for framework initialization and are used here within the context of the framework's intended purpose. - Promotion of Security Best Practices: The instructions include explicit warnings against insecure practices, such as hardcoding API keys or bot tokens, and direct the agent to follow established secret management patterns.
- Sandboxing for Untrusted Code: A key security feature of the skill is its recommendation to use isolated sandbox environments (via
skill:vercel-sandbox) when the agent needs to execute generated scripts or work with untrusted files, minimizing risk to the host system. - Reference to Official Documentation: The skill directs users and the agent to official documentation and repositories, ensuring that implementation details are sourced from authoritative and well-maintained origins.
Audit Metadata