write-mcp-eval
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a template generator for MCP server testing. It provides JSON schema examples and TypeScript test runner code that leverages the @gleanwork/mcp-server-tester package. As this package is owned by the skill's author ('gleanwork'), this represents standard vendor-provided functionality.
- [SAFE]: No suspicious network activity or data exfiltration patterns were detected. The skill mentions well-known LLM providers (Anthropic, OpenAI, Google) for evaluation purposes, which is consistent with its stated goal of testing AI models.
- [SAFE]: No obfuscation, prompt injection, or privilege escalation techniques were identified within the instructions or code examples.
Audit Metadata