agent-creator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official packages and tools from the
@modelcontextprotocolecosystem, such as the core SDK and inspector tool, which are standard for building MCP integrations. - [COMMAND_EXECUTION]: Provides guidance on using standard
npmandnpxcommands to manage dependencies and debug MCP servers. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a creation pipeline that transforms user-provided domain requirements into agent structures. This process is focused on design and documentation rather than immediate execution of untrusted data.
Audit Metadata