CVE-2026-54236

{
  "id": "CVE-2026-54236",
  "sourceIdentifier": "[email protected]",
  "published": "2026-06-22T23:16:31.290",
  "lastModified": "2026-10-25T23:10:00.167",
  "vulnStatus": "Analyzed",
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to clients without calling sanitize_message. The unsanitized sites include the Anthropic API router in vllm/entrypoints/anthropic/api_router.py (the POST /v1/messages and POST /v1/messages/count_tokens handlers), the Server-Sent Events streaming converter in vllm/entrypoints/anthropic/serving.py, and the realtime speech-to-text WebSocket in vllm/entrypoints/speech_to_text/realtime/connection.py. These paths catch the exception inside the route coroutine and construct the JSONResponse themselves, bypassing the sanitizing global FastAPI exception handler, and WebSocket frames do not traverse that handler chain at all. Using the same primitive as the parent issue, an unauthenticated attacker can send malformed image bytes through the Anthropic Messages API image content parts so that PIL.Image.open raises an UnidentifiedImageError whose message contains the BytesIO object repr, leaking the heap memory address verbatim in the error.message field of the response body. This vulnerability is fixed in 0.23.1rc0."
    },
    {
      "lang": "es",
      "value": "vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLMs). Antes de 0.23.1rc0, la corrección para CVE-2026-22778, que introdujo un gestor auxiliar sanitize_message que elimina las direcciones de memoria de representación de objetos de los mensajes de error antes de que lleguen al cliente, está incompleta: varias rutas de respuesta devuelven str(exc) directamente a los clientes sin llamar a sanitize_message. Los sitios no saneados incluyen el router de la API de Anthropic en vllm/entrypoints/anthropic/api_router.py (los gestores POST /v1/messages y POST /v1/messages/count_tokens), el conversor de streaming de Server-Sent Events en vllm/entrypoints/anthropic/serving.py, y el WebSocket de voz a texto en tiempo real en vllm/entrypoints/speech_to_text/realtime/connection.py. Estas rutas capturan la excepción dentro de la corrutina de la ruta y construyen la JSONResponse por sí mismas, omitiendo el gestor de excepciones global de FastAPI que realiza el saneamiento, y los frames de WebSocket no atraviesan esa cadena de gestores en absoluto. Usando la misma primitiva que el problema padre, un atacante no autenticado puede enviar bytes de imagen malformados a través de las partes de contenido de imagen de la API de Mensajes de Anthropic de modo que PIL.Image.open genere un UnidentifiedImageError cuyo mensaje contiene la representación del objeto BytesIO, filtrando la dirección de memoria del heap textualmente en el campo error.message del cuerpo de la respuesta. Esta vulnerabilidad está corregida en 0.23.1rc0."
    }
  ],
  "affected": [
    {
      "source": "[email protected]",
      "affectedData": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "versions": [
            {
              "version": "< 0.23.1rc0",
              "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:L/I:N/A:N",
          "baseScore": 5.3,
          "baseSeverity": "MEDIUM",
          "attackVector": "NETWORK",
          "attackComplexity": "LOW",
          "privilegesRequired": "NONE",
          "userInteraction": "NONE",
          "scope": "UNCHANGED",
          "confidentialityImpact": "LOW",
          "integrityImpact": "NONE",
          "availabilityImpact": "NONE"
        },
        "exploitabilityScore": 3.9,
        "impactScore": 1.4
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "timestamp": "2026-06-23T12:32:56.752434Z",
          "id": "CVE-2026-54236",
          "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-532"
        }
      ]
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "operator": "OR",
          "negate": false,
          "cpeMatch": [
            {
              "vulnerable": true,
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "versionEndExcluding": "0.23.1",
              "matchCriteriaId": "BF7F1CE7-1A95-41E3-95A5-732906527D08"
            }
          ]
        }
      ]
    }
  ],
  "references": [
    {
      "url": "https://github.com/vllm-project/vllm/commit/94923629729381d7f7c9efde72071a2441f7fd82",
      "source": "[email protected]",
      "tags": [
        "Patch"
      ]
    },
    {
      "url": "https://github.com/vllm-project/vllm/pull/45119",
      "source": "[email protected]",
      "tags": [
        "Issue Tracking"
      ]
    },
    {
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw",
      "source": "[email protected]",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ]
    },
    {
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-hgg8-fqqc-vfmw",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "tags": [
        "Exploit",
        "Third Party Advisory"
      ]
    }
  ]
}