← Back to CVE Explorer

CVE-2026-48814

Full vulnerability record from the local CVENow database.

Description

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.

Severity
CRITICAL
CVSS score
9.1 (v3.1)
Vulnerability status
Deferred
Source identifier
Published
2026-06-17 20:17:22.260000
Last modified
2026-10-25 23:10:00.167000
View original CVE JSON
{
  "id": "CVE-2026-48814",
  "sourceIdentifier": "[email protected]",
  "published": "2026-06-17T20:17:22.260",
  "lastModified": "2026-10-25T23:10:00.167",
  "vulnStatus": "Deferred",
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "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."
    },
    {
      "lang": "es",
      "value": "Network-AI es un orquestador multiagente de TypeScript/Node.js. En las versiones 5.7.1 y anteriores, el servidor SSE de MCP permite la invocación de herramientas MCP de origen cruzado no autenticada debido a un secreto predeterminado vacío. Este problema fue abordado parcialmente por CVE-2026-46701 en la versión 5.4.5 al cerrar la falla de CORS (con Access-Control-Allow-Origin ahora configurado solo para orígenes de localhost), pero la falla del secreto predeterminado vacío descrita en el título permaneció: el servidor SSE de MCP todavía usaba un secreto vacío por defecto, _isAuthorized() todavía devolvía verdadero cuando el secreto estaba vacío, y un enlace no-loopback solo producía una advertencia. Como resultado, el servidor todavía se ejecutaba completamente sin autenticación por defecto. Cualquier llamador que no sea un navegador (por ejemplo, curl, SSRF, o un enlace 0.0.0.0) podía invocar las 22 herramientas MCP (config_set, agent_spawn, blackboard_write, token_*) sin credenciales. Este problema fue solucionado en la versión 5.7.2."
    }
  ],
  "affected": [
    {
      "source": "[email protected]",
      "affectedData": [
        {
          "vendor": "Jovancoding",
          "product": "Network-AI",
          "versions": [
            {
              "version": "< 5.7.2",
              "status": "affected"
            }
          ]
        }
      ]
    }
  ],
  "metrics": {
    "cvssMetricV31": [
      {
        "source": "[email protected]",
        "type": "Secondary",
        "cvssData": {
          "version": "3.1",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N",
          "baseScore": 9.1,
          "baseSeverity": "CRITICAL",
          "attackVector": "NETWORK",
          "attackComplexity": "LOW",
          "privilegesRequired": "NONE",
          "userInteraction": "NONE",
          "scope": "UNCHANGED",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "availabilityImpact": "NONE"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 5.2
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "timestamp": "2026-06-18T19:42:39.963767Z",
          "id": "CVE-2026-48814",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "version": "2.0.3"
        }
      }
    ]
  },
  "weaknesses": [
    {
      "source": "[email protected]",
      "type": "Secondary",
      "description": [
        {
          "lang": "en",
          "value": "CWE-306"
        }
      ]
    }
  ],
  "references": [
    {
      "url": "https://github.com/Jovancoding/Network-AI/releases/tag/v5.7.2",
      "source": "[email protected]"
    },
    {
      "url": "https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-r78r-rwrf-rjwp",
      "source": "[email protected]"
    },
    {
      "url": "https://github.com/advisories/GHSA-j3vx-cx2r-pvg8",
      "source": "[email protected]"
    },
    {
      "url": "https://github.com/Jovancoding/Network-AI/security/advisories/GHSA-r78r-rwrf-rjwp",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ]
}