CVE Tools
Track your stack

CVE-2026-46701

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

No known exploitation. EPSS puts it in the 11th percentile. Fixed in 5.4.5.

CVSS 3.17.6HighEPSS percentile11th0.2% chance in 30 daysCISA KEVNot listedNo confirmed exploitation
No public exploit knownFix5.4.5Upgrade to this build
Check it yourself

No ready-made check. Neither Nuclei nor OpenVAS has one for this CVE yet.

Request a scan

Published Updated Sources: CVE.org, NVD

NVD CVE.org

What to do

Find your product and version, then upgrade to the build on the right.

  • Jovancoding Network-AIAffected: < 5.4.5Upgrade to: not statedStated by: CVE record
  • Network-aiAffected: < 5.4.5Upgrade to: 5.4.5Stated by: NVD

Versions as the sources state them. Full version matrix after sign-in

Is your organisation exposed?Request an assessment to establish which checks fit your systems.

What it is

From the CVE record

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.

In plain language

No plain-language summary for this CVE yet.

Exploitation

Where each signal puts this CVE on the scale from published to confirmed exploited.

EPSS11th
CISA KEV

Not in the catalog. CISA has not confirmed exploitation.

Public exploits

No public exploit or proof of concept found in the sources we track.

EPSS

0.2% chance of exploitation activity in the next 30 days, which ranks it in the 11th percentile of scored CVEs.

Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.

Lifecycle

10 events over 96 days, from the signal feeds we watch.

  1. Patch availableworkaround available, record updated
  2. Patch availableworkaround available, record updated
  3. Record updated
  4. Publishedweakness classified, record updated

Affected products

Technical detail

CVSS 3.1 vector

Open in the CVSS calculator

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L

Scored 7.6 by NVD.

How it is reached

  • Attack Vector NetworkExploitable remotely over the network without any special conditions
  • Attack Complexity LowNo special conditions — the attack can be reliably reproduced
  • Privileges Required NoneNo authentication required — anyone can exploit this
  • User Interaction RequiredA user must click a link, open a file, or perform some action

Scope

  • Scope UnchangedImpact is limited to the vulnerable component itself

Impact if exploited

  • Confidentiality LowSome restricted information is disclosed, but limited in scope
  • Integrity HighTotal loss of integrity — attacker can modify any data in the component
  • Availability LowReduced performance or intermittent disruption of service

Weaknesses

Sources

References in the record

Watch the software you run.

My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.

We'll flag the next CVE, public exploit or patch for Network-AI, not every advisory.