create-mcp-eval

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a code generation assistant, providing templates for test suites. No malicious patterns such as prompt injection, unauthorized data access, or obfuscation were detected.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to generate code that depends on standard development tools and libraries, including @mcpjam/sdk, vitest, and jest. These are legitimate dependencies within the context of the skill's purpose.
  • [DATA_EXFILTRATION]: While the generated code includes a reporter for MCPJam, this is a core feature of the tool and requires a user-provided API key. There is no evidence of unauthorized data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 02:14 PM
Security Audit — agent-trust-hub — create-mcp-eval