mcp-builder
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill guides the user to install official packages
mcpand@modelcontextprotocol/sdkfrom standard registries. It also references a debugging tool from a trusted vendor. - [INDIRECT_PROMPT_INJECTION]: The provided code templates include functionality for ingesting data from external APIs, local files, and databases. The skill describes these as standard integration patterns and includes a section on security best practices, such as input validation and limiting tool scope.
- [SAFE]: The content is educational in nature, providing boilerplate code for a standardized protocol and utilizing well-known service providers for examples.
Audit Metadata