« Volver al listado

CVE-2026-105755

Estado: En análisisMedia (4.2)—

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. 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.

Inferido por reglas deterministas a partir del vector CVSS y la CWE. Solo orientativo.

🛡️ Mitigaciones ATT&CK que cubren estas técnicas

Vulnerability ScanningThreat Intelligence ProgramPrivileged Account ManagementNetwork SegmentationDisable or Remove Feature or ProgramApplication Isolation and Sandboxing

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-2026-105755",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-105755",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-10-06T17:55:11.724369Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 4.2,
          "attackVector": "NETWORK",
          "baseSeverity": "MEDIUM",
          "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L",
          "integrityImpact": "LOW",
          "userInteraction": "NONE",
          "attackComplexity": "HIGH",
          "availabilityImpact": "LOW",
          "privilegesRequired": "LOW",
          "confidentialityImpact": "NONE"
        },
        "impactScore": 2.5,
        "exploitabilityScore": 1.6
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "versions": [
            {
              "status": "affected",
              "version": "< 030.0"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-10-05T23:17:02.167",
  "references": [
    {
      "url": "https://github.com/vllm-project/vllm/commit/ee17d0d869203ef9a35ad73358a4987bba14b1fc",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/pull/51445",
      "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-2phq-3phc-84px",
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Undergoing Analysis",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-639"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0."
    }
  ],
  "lastModified": "2026-10-06T18:16:46.240",
  "sourceIdentifier": "security-advisories@github.com"
}