mcp-gateway

The core functionality of the MCP Gateway involves executing user-defined commands and arguments for each configured MCP server using `child_process.spawn`. These commands are sourced directly from the `~/.mcp-gateway/config.json` file, which is user-editable. If this configuration file is compromised or a malicious entry is injected (e.g., through a malicious marketplace server listed in the desktop app, or by direct file modification), it could lead to arbitrary code execution (RCE) on the host system. Environment variables specified in the config are also passed directly to these spawned child processes, posing a risk of credential exfiltration if a malicious command is executed. While the user explicitly configures these commands, the gateway itself does not provide sandboxing for them, making configuration integrity critical. The README correctly advises securing the config file permissions (e.g., `chmod 600`).