CVE-2026-46701
Received Received - Intake

Unauthenticated Remote Code Execution in Network-AI MCP Server

Publication date: 2026-07-20

Last updated on: 2026-07-20

Assigner: GitHub, Inc.

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.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-07-20
Last Modified
2026-07-20
Generated
2026-07-21
AI Q&A
2026-07-20
EPSS Evaluated
N/A
NVD
CVE-2026-46701
EUVD
EUVD-2026-46019

Affected Vendors & Products

Showing 2 associated CPEs
Vendor Product Version / Range
jovancoding network-ai to 5.4.5 (exc)
jovancoding network-ai 5.4.5

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-346 The product does not properly verify that the source of data or communication is valid.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability in Network-AI (CVE-2026-46701) is a high-severity flaw where the MCP SSE server defaults to an empty secret, allowing unauthorized access. The server does not require an Authorization header and sets Access-Control-Allow-Origin to wildcard, enabling any cross-origin web page to invoke MCP tools without credentials.

Detection Guidance

Check if Network-AI SSE server is running on versions <= 5.4.4 by inspecting the process or package version. Verify if the server allows cross-origin requests with wildcard CORS headers and no secret requirement. Use curl to test: curl -H 'Origin: http://attacker.com' http://localhost:PORT/sse -I to check CORS headers.

Impact Analysis

An attacker could trick a user into visiting a malicious web page, which would then silently invoke MCP tools on a default-configured localhost server. This could lead to unauthorized configuration changes, data exposure, or other malicious actions depending on the tools accessed.

Compliance Impact

This vulnerability could lead to unauthorized access and data exposure, potentially violating GDPR (data protection) and HIPAA (health data privacy) by allowing attackers to read or modify sensitive information without consent.

Mitigation Strategies

Upgrade Network-AI to version 5.4.5 or later. Set a non-empty secret via NETWORK_AI_MCP_SECRET environment variable or command line. Restrict CORS to localhost origins by updating server configuration. Stop using affected versions if upgrade is not possible.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-46701. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart