CVE-2026-105756

Status: Undergoing AnalysisMedium (6.5)—

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. This issue is fixed in version 0.30.0.

CVSS

Version: 3.1
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Base score: 6.5

Exploitation probability (EPSS)

Probability of exploitation in the next 30 days: 0.31%
Percentile among all scored CVEs: 22
Score date: 10/7/2026

EPSS (Exploit Prediction Scoring System, FIRST) estimates how likely a vulnerability is to be exploited in the wild within 30 days. It complements CVSS (impact) and CISA KEV (confirmed exploitation).

🎯 ATT&CK techniques

How this vulnerability is exploited and what the attacker gains, in MITRE ATT&CK terms.

ExploitationT1210 Exploitation of Remote Serviceslateral movement85 %
Primary impactT1499 Endpoint Denial of Serviceimpact90 %

Vulnerabilidad remota (AV:N, PR:L) en vLLM que causa DoS; parámetro cache_salt sin validación genera ValueError no capturado, deteniendo EngineCore y negando servicio a usuarios concurrentes.

Inferred by our analysis agent from the official description, CVSS vector and CWE, and checked by a supervisor. May contain errors.

🛡️ ATT&CK mitigations that cover these techniques

Vulnerability Scanning Threat Intelligence Program Privileged Account Management Network Segmentation Filter Network Traffic Disable or Remove Feature or Program

Affected technologies (1)

⚠ AI-inferred from the description — NVD hasn't analyzed this CVE yet, these aren't verified CPEs.

Vllm — Vllm^AI

CWEs

CWE-20, CWE-248

References

Raw JSON (NVD)

Show

{
  "id": "CVE-2026-105756",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-105756",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-10-06T14:41:36.857213Z"
        }
      }
    ],
    "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": "2026-10-05T23:17:02.317",
  "references": [
    {
      "url": "https://github.com/vllm-project/vllm/commit/e962733e08d10f7ca65dac4df99e116460b8b174",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/vllm-project/vllm/pull/51444",
      "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-2823-qmq8-rwvj",
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Undergoing Analysis",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-20"
        },
        {
          "lang": "en",
          "value": "CWE-248"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is an inference and serving engine for large language models. Prior to 0.30.0, OpenAI-compatible request models accept a non-empty cache_salt value without enforcing the character and length restrictions required by the IPCCacheServerKey consumer in LMCache-MP. On deployments using the LMCache-MP connector, a salt that contains a forbidden character or exceeds the permitted length can raise an uncaught ValueError during scheduler cache lookup, causing EngineCore to terminate and denying service to all concurrent users. This issue is fixed in version 0.30.0."
    }
  ],
  "lastModified": "2026-10-06T15:17:15.150",
  "sourceIdentifier": "security-advisories@github.com"
}