« Volver al listado

CVE-2025-47277

Estado: AnalizadaCrítica (9.8)—

vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the `PyNcclPipe` class to establish a peer-to-peer communication domain for data transmission between distributed nodes.

Leer descripción completaMostrar menos

The GPU-side KV-Cache transmission is implemented through the `PyNcclCommunicator` class, while CPU-side control message passing is handled via the `send_obj` and `recv_obj` methods on the CPU side.​ The intention was that this interface should only be exposed to a private network using the IP address specified by the `--kv-ip` CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the `TCPStore` interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the `TCPStore` instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the `TCPStore` socket to the private interface as configured.

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 (PR:N, UI:N) expone API PyNcclPipe; CVSS indica confidencialidad, integridad y disponibilidad críticas. Ejecución remota de código en el servidor vLLM, potencial escalada a privilegios del proceso GPU.

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

Vulnerability ScanningPrivileged Account ManagementNetwork SegmentationLimit Access to Resource Over NetworkFilter Network TrafficApplication Isolation and Sandboxing

Tecnologías afectadas (1)

Vllm — Vllm

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2025-47277",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2025-47277",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2025-05-20T17:52:22.643444Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.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": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "versions": [
            {
              "status": "affected",
              "version": ">= 0.6.5, < 0.8.5"
            }
          ]
        }
      ]
    }
  ],
  "published": "2025-05-20T18:15:46.730",
  "references": [
    {
      "url": "https://docs.vllm.ai/en/latest/deployment/security.html",
      "tags": [
        "Technical Description"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/commit/0d6e187e88874c39cda7409cf673f9e6546893e7",
      "tags": [
        "Patch"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/pull/15988",
      "tags": [
        "Issue Tracking",
        "Patch"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hjq4-87xh-g4fv",
      "tags": [
        "Exploit",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-502"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4 that ONLY impacts environments using the `PyNcclPipe` KV cache transfer integration with the V0 engine. No other configurations are affected. vLLM supports the use of the `PyNcclPipe` class to establish a peer-to-peer communication domain for data transmission between distributed nodes. The GPU-side KV-Cache transmission is implemented through the `PyNcclCommunicator` class, while CPU-side control message passing is handled via the `send_obj` and `recv_obj` methods on the CPU side.​ The intention was that this interface should only be exposed to a private network using the IP address specified by the `--kv-ip` CLI parameter. The vLLM documentation covers how this must be limited to a secured network. The default and intentional behavior from PyTorch is that the `TCPStore` interface listens on ALL interfaces, regardless of what IP address is provided. The IP address given was only used as a client-side address to use. vLLM was fixed to use a workaround to force the `TCPStore` instance to bind its socket to a specified private interface. As of version 0.8.5, vLLM limits the `TCPStore` socket to the private interface as configured."
    },
    {
      "lang": "es",
      "value": "vLLM, un motor de inferencia y servicio para modelos de lenguaje grandes (LLM), presenta un problema en las versiones 0.6.5 a 0.8.4 que SOLO afecta a entornos que utilizan la integración de transferencia de caché KV `PyNcclPipe` con el motor V0. Ninguna otra configuración se ve afectada. vLLM admite el uso de la clase `PyNcclPipe` para establecer un dominio de comunicación punto a punto para la transmisión de datos entre nodos distribuidos. La transmisión de caché KV del lado de la GPU se implementa mediante la clase `PyNcclCommunicator`, mientras que el paso de mensajes de control del lado de la CPU se gestiona mediante los métodos `send_obj` y `recv_obj` en el lado de la CPU. El objetivo era que esta interfaz solo se expusiera a una red privada utilizando la dirección IP especificada por el parámetro de CLI `--kv-ip`. La documentación de vLLM explica cómo esto debe limitarse a una red segura. El comportamiento predeterminado e intencional de PyTorch es que la interfaz `TCPStore` escucha en TODAS las interfaces, independientemente de la dirección IP proporcionada. La dirección IP proporcionada solo se usaba como dirección del cliente. vLLM se corrigió para usar una solución alternativa que obligaba a la instancia `TCPStore` a vincular su socket a una interfaz privada específica. A partir de la versión 0.8.5, vLLM limita el socket `TCPStore` a la interfaz privada configurada."
    }
  ],
  "lastModified": "2026-06-17T09:27:39.253",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "24BAE45E-0FCF-4E74-953A-88F12E093C0F",
              "versionEndExcluding": "0.8.5",
              "versionStartIncluding": "0.6.5"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}