CVE-2026-46701: Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret

Severity: high (CVSS 7.6 v3.1)
Exploited in the wild: not listed in CISA KEV
EPSS: 0.2% probability of exploitation in the next 30 days
Public exploit or detection template: yes
Published: 2026-07-20 · updated 2026-10-24
Weakness: CWE-346

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

Jovancoding Network-AI: before 5.4.5 — fixed in 5.4.5

How to fix

Upgrade to a fixed version: Jovancoding Network-AI 5.4.5. Check the vendor advisory for mitigations.

References

Get alerted when CVE-2026-46701 or the next vulnerability affects your stack