mcp-developer
Pass
Audited by Gen Agent Trust Hub on Aug 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a technical reference and documentation guide for implementing the Model Context Protocol (MCP). It contains instructional content, code examples for TypeScript and Python SDKs, and protocol specifications.
- [COMMAND_EXECUTION]: The skill mentions standard initialization and debugging commands such as
npx @modelcontextprotocol/create-serverandnpx @modelcontextprotocol/inspector. These are well-known developer tools for the MCP ecosystem and do not represent a security risk. - [EXTERNAL_DOWNLOADS]: The skill references standard package managers (
pip install mcp,npm install @modelcontextprotocol/sdk) to install official SDKs. These downloads target well-known package registries and official repositories. - [DATA_EXPOSURE]: The instructions explicitly include constraints such as 'MUST NOT DO: Expose sensitive data in resource content' and 'MUST NOT DO: Hardcode credentials or secrets', promoting secure coding practices.
- [PROMPT_INJECTION]: No evidence of prompt injection patterns or attempts to override agent behavior was detected. The instructions are purely technical and focused on protocol implementation.
Audit Metadata