« Volver al listado

CVE-2026-105754

Estado: En análisisMedia (6.5)—

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract.

Leer descripción completaMostrar menos

Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0.

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.

Acceso remoto con autenticación (PR:L) a endpoint /inference/v1/generate que acepta datos sin validar (CWE-20): DoS por terminación del EngineCore (A:H), envenenamiento de caché para alterar o exfiltrar estado compartido, y lectura de caché de sesiones cruzadas.

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 ScanningThreat Intelligence ProgramRestrict File and Directory PermissionsPrivileged Account ManagementRemote Data StorageNetwork Segmentation

Tecnologías afectadas (1)

⚠ Inferidas por IA a partir de la descripción — NVD aún no ha analizado esta CVE; no son CPE verificados.

Vllm — VllmAI

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2026-105754",
  "cveTags": [],
  "metrics": {
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 6.5,
          "attackVector": "NETWORK",
          "baseSeverity": "MEDIUM",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H",
          "integrityImpact": "NONE",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "LOW",
          "confidentialityImpact": "NONE"
        },
        "impactScore": 3.6,
        "exploitabilityScore": 2.8
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "versions": [
            {
              "status": "affected",
              "version": "< 0.30.0"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-10-05T23:17:02.017",
  "references": [
    {
      "url": "https://github.com/vllm-project/vllm/commit/1970f3ed4be7fa8620e4ddc4a12c36a8384cfc27",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/pull/51898",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/releases/tag/v0.30.0",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-ph72-cqr5-qpp7",
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Undergoing Analysis",
  "weaknesses": [
    {
      "type": "Primary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-20"
        },
        {
          "lang": "en",
          "value": "CWE-617"
        },
        {
          "lang": "en",
          "value": "CWE-639"
        },
        {
          "lang": "en",
          "value": "CWE-668"
        },
        {
          "lang": "en",
          "value": "CWE-704"
        },
        {
          "lang": "en",
          "value": "CWE-1284"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is an inference and serving engine for large language models. Prior to 0.30.0, the /inference/v1/generate endpoint in the disaggregated scale-out path accepts caller-supplied tensors in the features.kwargs_data field, cache identifiers in the features.mm_hashes field, ranges in the features.mm_placeholders field, and wire-selected multimodal field processors without rebinding them to the active model renderer contract. Forged grid geometry, field types, or non-positive placeholder lengths can terminate the shared EngineCore; when an attacker knows or can induce a victim's content hash, forged cache hashes can poison or retrieve cross-request encoder-cache state; and dropped sparse placeholder masks can alter replayed transport semantics. This issue is fixed in version 0.30.0."
    }
  ],
  "lastModified": "2026-10-06T14:59:48.280",
  "sourceIdentifier": "security-advisories@github.com"
}