CVE-2026-48814
Brak uwierzytelnienia w serwerze MCP SSE w Network-AI pozwala na nieautoryzowane wywołania narzędzi.
Network-AI is a TypeScript/Node.js multi-agent orchestrator. In versions 5.7.1 and earlier, the MCP SSE server allows unauthenticated cross-origin MCP tool invocation due to an empty default secret. This issue was partially addressed by CVE-2026-46701 in version 5.4.5 by closing the CORS flaw (with Access-Control-Allow-Origin now set only for localhost origins), but the empty-default-secret flaw described in the title remained: the SSE MCP server still defaulted to an empty secret, _isAuthorized() still returned true when the secret was empty, and a non-loopback bind only produced a warning. As a result, the server still ran fully unauthenticated by default. Any non-browser caller (for example, curl, SSRF, or a 0.0.0.0 bind) could invoke all 22 MCP tools (config_set, agent_spawn, blackboard_write, token_*) with no credentials. This issue was fixed in version 5.7.2.
| Źródło | Wartość |
|---|---|
| NVD – CVSS | 9.1 |
| CISA KEV (aktywnie wykorzystywane) | Nie |
| FIRST EPSS (prawdopodobieństwo exploita) | 0.3% |
| Opublikowano (NVD) | 2026-06-17 20:17:22 UTC |
| Ostatnia modyfikacja (NVD) | 2026-06-23 15:50:59 UTC |
- https://github.com/Jovancoding/Network-AI/releases/tag/v5.7.2 (security-advisories@github.com)
- https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-r78r-rwrf-rjwp (security-advisories@github.com)
- https://github.com/advisories/GHSA-j3vx-cx2r-pvg8 (security-advisories@github.com)