mcp-server-testing
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill utilizes official Model Context Protocol tools via npx (@modelcontextprotocol/inspector, @modelcontextprotocol/conformance). These are standard tools for MCP development and are fetched from legitimate registries.
- [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/lint_eval_suite.py) to validate evaluation files. The script uses standard libraries and does not perform dangerous operations.
- [SAFE]: References to external repositories like github.com/anthropics/skills point to trusted organizations. Load-test templates provided in the documentation use best practices for secret management, specifically recommending the use of environment variables rather than hardcoded credentials.
Audit Metadata