← Back to CVE Explorer

CVE-2026-43632

Full vulnerability record from the local CVENow database.

Description

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured.

Severity
CRITICAL
CVSS score
9.2 (v4.0)
Vulnerability status
Analyzed
Source identifier
Published
2026-08-06 22:17:06.343000
Last modified
2026-10-23 21:10:00.157000
View original CVE JSON
{
  "id": "CVE-2026-43632",
  "sourceIdentifier": "[email protected]",
  "published": "2026-08-06T22:17:06.343",
  "lastModified": "2026-10-23T21:10:00.157",
  "vulnStatus": "Analyzed",
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured."
    },
    {
      "lang": "es",
      "value": "Las compilaciones de llama.cpp desde la b7492 hasta la última b9060 contienen una vulnerabilidad de uso después de liberación en llama-server que afecta a seis puntos finales de tokenización (/tokenize, /detokenize, /infill, /apply-template, /rerank, y /anthropic/count_tokens) que omiten la cola de tareas y acceden directamente a ctx_server.vocab en los hilos de trabajo HTTP. Los atacantes pueden explotar una condición de carrera de tiempo de verificación-tiempo de uso donde el hilo principal destruye y libera vocab después de que se libera el bloqueo de sincronización pero antes de que el gestor termine de usarlo, causando un fallo o una posible ejecución de código cuando se configura --sleep-idle-seconds."
    }
  ],
  "affected": [
    {
      "source": "[email protected]",
      "affectedData": [
        {
          "vendor": "ggml-org",
          "product": "llama.cpp",
          "defaultStatus": "affected",
          "versions": [
            {
              "version": "b7492",
              "lessThanOrEqual": "b9060",
              "versionType": "custom",
              "status": "affected"
            }
          ]
        }
      ]
    }
  ],
  "metrics": {
    "cvssMetricV40": [
      {
        "source": "[email protected]",
        "type": "Secondary",
        "cvssData": {
          "version": "4.0",
          "vectorString": "CVSS:4.0/AV:N/AC:H/AT:P/PR:N/UI:N/VC:H/VI:H/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",
          "baseScore": 9.2,
          "baseSeverity": "CRITICAL",
          "attackVector": "NETWORK",
          "attackComplexity": "HIGH",
          "attackRequirements": "PRESENT",
          "privilegesRequired": "NONE",
          "userInteraction": "NONE",
          "vulnConfidentialityImpact": "HIGH",
          "vulnIntegrityImpact": "HIGH",
          "vulnAvailabilityImpact": "HIGH",
          "subConfidentialityImpact": "NONE",
          "subIntegrityImpact": "NONE",
          "subAvailabilityImpact": "NONE",
          "exploitMaturity": "NOT_DEFINED",
          "confidentialityRequirement": "NOT_DEFINED",
          "integrityRequirement": "NOT_DEFINED",
          "availabilityRequirement": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "Safety": "NOT_DEFINED",
          "Automatable": "NOT_DEFINED",
          "Recovery": "NOT_DEFINED",
          "valueDensity": "NOT_DEFINED",
          "vulnerabilityResponseEffort": "NOT_DEFINED",
          "providerUrgency": "NOT_DEFINED"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "source": "[email protected]",
        "type": "Secondary",
        "cvssData": {
          "version": "3.1",
          "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H",
          "baseScore": 8.1,
          "baseSeverity": "HIGH",
          "attackVector": "NETWORK",
          "attackComplexity": "HIGH",
          "privilegesRequired": "NONE",
          "userInteraction": "NONE",
          "scope": "UNCHANGED",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "availabilityImpact": "HIGH"
        },
        "exploitabilityScore": 2.2,
        "impactScore": 5.9
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "timestamp": "2026-08-08T02:09:08.150856Z",
          "id": "CVE-2026-43632",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "version": "2.0.3"
        }
      }
    ]
  },
  "weaknesses": [
    {
      "source": "[email protected]",
      "type": "Secondary",
      "description": [
        {
          "lang": "en",
          "value": "CWE-367"
        },
        {
          "lang": "en",
          "value": "CWE-416"
        }
      ]
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "operator": "OR",
          "negate": false,
          "cpeMatch": [
            {
              "vulnerable": true,
              "criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
              "versionStartIncluding": "b7492",
              "versionEndIncluding": "b9060",
              "matchCriteriaId": "0809463E-7195-4AD2-90E6-1CE6A05CC8BA"
            }
          ]
        }
      ]
    }
  ],
  "references": [
    {
      "url": "https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches",
      "source": "[email protected]",
      "tags": [
        "Patch",
        "Third Party Advisory"
      ]
    },
    {
      "url": "https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints",
      "source": "[email protected]",
      "tags": [
        "Patch",
        "Third Party Advisory"
      ]
    }
  ]
}