CVE-2026-46701 Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret
- Published
- Updated
- Exploit status
- No public exploit known
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.
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| Jovancoding Network-AI | = < 5.4.5 | No fix listed |
| npm network-ai(npm) | <= 5.4.4 | No fix listed |
| network-ai | < 5.4.5 | 5.4.5 |
References
- https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-j3vx-cx2r-pvg8 exploit mitigation vendor-advisory
- https://github.com/Jovancoding/Network-AI/commit/dc5048112283f3f4eb6c06dd2bf5aa93ef9339be patch
- https://github.com/Jovancoding/Network-AI/releases/tag/v5.4.5 patch release-notes
- github.com