mcp-expert

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary purpose is to act as a technical reference for MCP development. It contains no malicious instructions or hidden behaviors.
  • [EXTERNAL_DOWNLOADS]: The skill references standard, well-known Node.js packages including @modelcontextprotocol/sdk and zod which are required for the protocol's implementation. These are treated as safe dependencies for this domain.
  • [PROMPT_INJECTION]: No attempts to bypass agent safety filters or override system instructions were found.
  • [DATA_EXFILTRATION]: No unauthorized network operations or sensitive file access patterns were detected. The skill specifically promotes security best practices such as input validation and using parameterized queries to prevent SQL injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:54 AM