« Volver al listado

CVE-2026-100651

Estado: En análisisAlta (7.1)—

vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied token_ids, and GenerateRequest.token_ids (vllm/entrypoints/serve/disagg/protocol.py) is not checked against model_config.max_model_len.

Leer descripción completaMostrar menos

For multimodal processors that report skip_prompt_length_check=True (for example Nemotron Parse, Whisper, and FireRedLID), InputProcessor._validate_prompt_len() returns immediately for both encoder and decoder prompts, so an overlong prompt becomes an EngineCoreRequest and reaches the worker input-batch copy into a fixed max_model_len-wide NumPy row. A client able to reach the endpoint on an affected model configuration can therefore submit an overlong token_ids list to trigger a worker failure and denial of service. Fixed in 0.29.0.

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.

Explotación de servicio remoto (/inference/v1/generate) sin validación de longitud de prompt que causa fallo en worker (DoS por Application Exhaustion). AV:N, PR:L, VA:H confirma impacto de disponibilidad.

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 ProgramPrivileged Account ManagementNetwork SegmentationFilter Network TrafficDisable or Remove Feature or Program

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-2026-100651",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-100651",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-09-28T18:21:26.899493Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "disclosure@vulncheck.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
      }
    ],
    "cvssMetricV40": [
      {
        "type": "Secondary",
        "source": "disclosure@vulncheck.com",
        "cvssData": {
          "Safety": "NOT_DEFINED",
          "version": "4.0",
          "Recovery": "NOT_DEFINED",
          "baseScore": 7.1,
          "Automatable": "NOT_DEFINED",
          "attackVector": "NETWORK",
          "baseSeverity": "HIGH",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
          "exploitMaturity": "NOT_DEFINED",
          "providerUrgency": "NOT_DEFINED",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "attackRequirements": "NONE",
          "privilegesRequired": "LOW",
          "subIntegrityImpact": "NONE",
          "vulnIntegrityImpact": "NONE",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "subAvailabilityImpact": "NONE",
          "vulnAvailabilityImpact": "HIGH",
          "availabilityRequirement": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "subConfidentialityImpact": "NONE",
          "vulnConfidentialityImpact": "NONE",
          "confidentialityRequirement": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "vulnerabilityResponseEffort": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED"
        }
      }
    ]
  },
  "affected": [
    {
      "source": "disclosure@vulncheck.com",
      "affectedData": [
        {
          "vendor": "vllm-project",
          "product": "vllm",
          "versions": [
            {
              "status": "affected",
              "version": "0",
              "lessThan": "0.29.0",
              "versionType": "semver"
            },
            {
              "status": "unaffected",
              "version": "0.29.0",
              "versionType": "semver"
            }
          ],
          "packageURL": "pkg:pypi/vllm",
          "defaultStatus": "unaffected"
        }
      ]
    }
  ],
  "published": "2026-09-26T14:16:47.663",
  "references": [
    {
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-3mqx-f33v-vgp9",
      "source": "disclosure@vulncheck.com"
    },
    {
      "url": "https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-decoder-prompt-length-bypass",
      "source": "disclosure@vulncheck.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-3mqx-f33v-vgp9",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ],
  "vulnStatus": "Undergoing Analysis",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "disclosure@vulncheck.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-400"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied token_ids, and GenerateRequest.token_ids (vllm/entrypoints/serve/disagg/protocol.py) is not checked against model_config.max_model_len. For multimodal processors that report skip_prompt_length_check=True (for example Nemotron Parse, Whisper, and FireRedLID), InputProcessor._validate_prompt_len() returns immediately for both encoder and decoder prompts, so an overlong prompt becomes an EngineCoreRequest and reaches the worker input-batch copy into a fixed max_model_len-wide NumPy row. A client able to reach the endpoint on an affected model configuration can therefore submit an overlong token_ids list to trigger a worker failure and denial of service. Fixed in 0.29.0."
    }
  ],
  "lastModified": "2026-09-28T21:03:04.910",
  "sourceIdentifier": "disclosure@vulncheck.com"
}