mcp-management
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation and management tools for Model Context Protocol (MCP) servers, which is a standard feature of the agent's environment.
- [CREDENTIALS_UNSAFE]: The skill promotes secure credential management by using environment variable placeholders in configuration examples instead of hardcoded secrets.
- [COMMAND_EXECUTION]: Shell commands provided (using jq, find, which) are intended for inspecting configuration files and verifying the availability of local development tools.
- [DATA_EXFILTRATION]: No patterns of unauthorized data transmission or exfiltration were detected; network operations are limited to standard OAuth flows and SSE transport for remote servers.
Audit Metadata