CVE-2026-46701
Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:LSummary
CVE-2026-46701 is a high-severity Origin Validation Error (CWE-346) vulnerability. Its CVSS base score is 7.6 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Drive-by Compromise (T1189); ranked at the 6th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.
The strongest mitigations our analysis identified map to AC-3 (Access Enforcement) and AC-4 (Information Flow Enforcement) — see the control section below for these in your framework.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-46019
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ai, mcp, mcp, mcp, mcp, mcp
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Missing auth + permissive CORS on localhost MCP server directly enables drive-by compromise via malicious webpage invoking exposed tools.
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
Mitigating Controls (NIST 800-53 r5) AI
Directly enforces authorization checks so that _isAuthorized cannot return true for unauthenticated cross-origin requests.
Enforces information flow policies that would block * origin CORS responses and restrict tool invocations to authorized origins only.
Boundary protection mechanisms can restrict localhost MCP endpoints from accepting requests originating from untrusted external web pages.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Authentication directly verifies the source of users/services/hardware, mitigating origin validation failures.
Verifying identity assertions enforces origin validation for conveyed claims.
Documenting authorized flows supports origin validation by defining expected sources.
Protecting networks from unauthorized access requires origin checks on communication sources.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Network security controls enforce origin validation at network boundaries.
Security of network services includes validating the authenticity of service endpoints.
Network segregation reduces exposure but does not directly validate origins.
Application security requirements explicitly call for origin validation of inputs and communications.
Secure architecture principles encourage origin checks but do not mandate them.
Secure coding practices include implementing proper origin validation to prevent spoofing.