Network-AI: Unauthenticated Cross-Origin MCP Tool Invocation via Empty Default Secret
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Required
- Attack complexity
- Low
- Impact type
- Security bypass
- Confidentiality · integrity · availability
- Low · High · Low
- Fix status
- Fixed
Attack profile from CVSS 3.1 · CNA. Fix status from CNA and GitHub. Impact type from CWE-346.
Summary
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| Jovancoding | Network-AI | before 5.4.5 | 5.4.5 | Patch available | CNA |
| — | network-ai (npm) | before 5.4.5 | 5.4.5 | Patch available | GHSA-j3vx-cx2r-pvg8 |
- Network-AI VendorJovancoding Affected before 5.4.5 Fixed in 5.4.5 Patch available CNA
- network-ai (npm) Vendor— Affected before 5.4.5 Fixed in 5.4.5 Patch available GHSA-j3vx-cx2r-pvg8
CPE configurations NVD · 1
| CPE | Versions | Role | Vendor |
|---|---|---|---|
| cpe:2.3:a:network-ai:network-ai:*:*:*:*:*:*:*:* | before 5.4.5 | Vulnerable | Jovancoding |
- cpe:2.3:a:network-ai:network-ai:*:*:*:*:*:*:*:* Versions before 5.4.5 Vulnerable ·Jovancoding
Remediation
- Fix · CNA Network-AI (Jovancoding) Fixed in 5.4.5
- Fix · GHSA-j3vx-cx2r-pvg8 network-ai (npm) Fixed in 5.4.5 Advisory →
Timeline
- 2026-10-02 Threatist record created from CVE-2026-46701
- 2026-10-03 Alias added: GHSA-j3vx-cx2r-pvg8
References
More Jovancoding Network-ai vulnerabilities
- TI-2026-42088 Network-AI: Poisoned environment backup manifest allows arbitrary recursive deletion during backup pruning CVSS 3.1HIGH 7.1
- TI-2026-42085 Network-AI: AgentRuntime sandbox path-prefix checks allow file access outside the configured base directory CVSS 3.1MEDIUM 6.5
- TI-2026-42086 Network-AI: ApprovalInbox HTTP server has no authentication — anyone can approve pending agent actions CVSS 3.1MEDIUM 5.9
- TI-2026-42024 EnvironmentManager.restore() backup ID path traversal copies arbitrary directories into environment data CVSS 3.1MEDIUM 6.1
- TI-2026-42025 Path traversal in Jovancoding Network-AI CVSS 3.1MEDIUM 5.5
Sources
- CVE-2026-46701 · CVE Program
- CVE-2026-46701 · NVD
- FIRST EPSS
- GHSA-j3vx-cx2r-pvg8 · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences