« Volver al listado

CVE-2025-23316

Estado: AnalizadaCrítica (9.8)—

NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause a remote code execution by manipulating the model name parameter in the model control APIs. A successful exploit of this vulnerability might lead to remote code execution, denial of service, information disclosure, and data tampering.

CVSS

Probabilidad de explotación (EPSS)

EPSS (Exploit Prediction Scoring System, de FIRST) estima la probabilidad de que una vulnerabilidad sea explotada en 30 días. Complementa a CVSS (impacto) y a CISA KEV (explotación confirmada).

🎯 Técnicas ATT&CK

Cómo se explota esta vulnerabilidad y qué consigue el atacante, en el lenguaje de MITRE ATT&CK.

Red sin autenticación (AV:N, PR:N, UI:N) permite RCE remota en APIs de control del modelo; CWE-78 (command injection) en backend Python genera ejecución de código, DoS y manipulación de datos.

Inferido por nuestro agente de análisis a partir de la descripción oficial, el vector CVSS y la CWE, y comprobado por un supervisor. Puede contener errores.

🛡️ Mitigaciones ATT&CK que cubren estas técnicas

Privileged Account ManagementFilter Network TrafficVulnerability ScanningRestrict Web-Based ContentRestrict File and Directory PermissionsRemote Data Storage

Tecnologías afectadas (1)

Nvidia — Triton Inference Server

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2025-23316",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2025-23316",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2025-09-18T14:01:46.640784Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "psirt@nvidia.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 9.8,
          "attackVector": "NETWORK",
          "baseSeverity": "CRITICAL",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
          "integrityImpact": "HIGH",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "HIGH"
        },
        "impactScore": 5.9,
        "exploitabilityScore": 3.9
      }
    ]
  },
  "affected": [
    {
      "source": "psirt@nvidia.com",
      "affectedData": [
        {
          "vendor": "NVIDIA",
          "product": "Triton Inference Server",
          "versions": [
            {
              "status": "affected",
              "version": "All versions prior to 25.08"
            }
          ],
          "platforms": [
            "Windows",
            "Linux"
          ],
          "defaultStatus": "unaffected"
        }
      ]
    }
  ],
  "published": "2025-09-17T22:15:37.260",
  "references": [
    {
      "url": "https://nvidia.custhelp.com/app/answers/detail/a_id/5691",
      "tags": [
        "Vendor Advisory"
      ],
      "source": "psirt@nvidia.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "psirt@nvidia.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-78"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause a remote code execution by manipulating the model name parameter in the model control APIs. A successful exploit of this vulnerability might lead to remote code execution, denial of service, information disclosure, and data tampering."
    },
    {
      "lang": "es",
      "value": "NVIDIA Triton Inference Server para Windows y Linux contiene una vulnerabilidad en el backend de Python, donde un atacante podría causar una ejecución remota de código manipulando el parámetro del nombre del modelo en las API de control del modelo. Un exploit exitoso de esta vulnerabilidad podría conducir a ejecución remota de código, denegación de servicio, revelación de información y manipulación de datos."
    }
  ],
  "lastModified": "2026-06-17T08:53:27.213",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:nvidia:triton_inference_server:*:*:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "3307464B-57D9-40E2-BDD4-F909F9E6FA32",
              "versionEndExcluding": "25.08"
            }
          ],
          "operator": "OR"
        },
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:o:linux:linux_kernel:-:*:*:*:*:*:*:*",
              "vulnerable": false,
              "matchCriteriaId": "703AF700-7A70-47E2-BC3A-7FD03B3CA9C1"
            },
            {
              "criteria": "cpe:2.3:o:microsoft:windows:-:*:*:*:*:*:*:*",
              "vulnerable": false,
              "matchCriteriaId": "A2572D17-1DE6-457B-99CC-64AFD54487EA"
            }
          ],
          "operator": "OR"
        }
      ],
      "operator": "AND"
    }
  ],
  "sourceIdentifier": "psirt@nvidia.com"
}