CyberRota Analysis
AI-GeneratedThe MCP SSE server in Network-AI versions prior to 5.4.5 is vulnerable due to a default empty secret, allowing unauthorized access to all exposed MCP tools without requiring an `Authorization` header. This flaw, combined with permissive CORS settings, enables unauthenticated attackers to exploit the server by luring users to malicious web pages, potentially leading to significant unauthorized actions on the server. Organizations using affected versions should prioritize upgrading to 5.4.5 to mitigate this high-severity vulnerability.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
Network-AI is a TypeScript/Node.js multi-agent orchestrator. Prior to version 5.4.5, the MCP SSE server defaults to an empty secret (`process.env['NETWORK_AI_MCP_SECRET'] ?? ''` at `bin/mcp-server.ts:89`), which causes `_isAuthorized` (`lib/mcp-transport-sse.ts:254`) to return `true` unconditionally for every request — no `Authorization` header is required. Simultaneously, `_handleRequest` sets `Access-Control-Allow-Origin: *` (`lib/mcp-transport-sse.ts:272`) on every response, so a cross-origin browser fetch can read the result without restriction. An unauthenticated attacker who can lure a user to a malicious web page can invoke all 22 exposed MCP tools — including `config_set`, `agent_spawn`, and `blackboard_write` — against a default-configured localhost server. Version 5.4.5 patches the issue.
Related CVEs
Other vulnerabilities affecting the same vendor(s)