CVE-2026-43632 (GCVE-0-2026-43632)

Vulnerability from cvelistv5 – Published: 2026-08-06 15:53 – Updated: 2026-08-08 02:09 X_Open Source
VLAI
Title
llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
Summary
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
9.2 (Critical)
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
8.1 (High)
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H
SSVC
Exploitation: none Automatable: no Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
  • CWE-416 - Use After Free
  • CWE-367 - Time-of-check Time-of-use (TOCTOU) Race Condition
Assigner
References
Impacted products
Vendor Product Version
ggml-org llama.cpp Affected: b7492 , ≤ b9060 (custom)
Create a notification for this product.
Date Public
2026-05-06 00:00
Credits
Vladimir Tokarev (@G1ND1L4) - Vulnerability Research Tech Lead, Cyera Ofek Itach (@ofekitach) - Security Research Team Lead, Cyera
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-43632",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-08-08T02:09:08.150856Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-08-08T02:09:18.676Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "affected",
          "product": "llama.cpp",
          "vendor": "ggml-org",
          "versions": [
            {
              "lessThanOrEqual": "b9060",
              "status": "affected",
              "version": "b7492",
              "versionType": "custom"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Vladimir Tokarev (@G1ND1L4) - Vulnerability Research Tech Lead, Cyera"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Ofek Itach (@ofekitach) - Security Research Team Lead, Cyera"
        }
      ],
      "datePublic": "2026-05-06T00:00:00.000Z",
      "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."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "HIGH",
            "attackRequirements": "PRESENT",
            "attackVector": "NETWORK",
            "baseScore": 9.2,
            "baseSeverity": "CRITICAL",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "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",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 8.1,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-416",
              "description": "Use After Free",
              "lang": "en",
              "type": "CWE"
            },
            {
              "cweId": "CWE-367",
              "description": "Time-of-check Time-of-use (TOCTOU) Race Condition",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-07T19:06:44.455Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "tags": [
            "mitigation"
          ],
          "url": "https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches"
        },
        {
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints"
        }
      ],
      "source": {
        "discovery": "EXTERNAL"
      },
      "tags": [
        "x_open-source"
      ],
      "title": "llama.cpp b7492\u2013b9060 Use-After-Free in Tokenization Endpoints",
      "x_generator": {
        "engine": "vulncheck"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-43632",
    "datePublished": "2026-08-06T15:53:19.379Z",
    "dateReserved": "2026-05-01T18:22:45.641Z",
    "dateUpdated": "2026-08-08T02:09:18.676Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-43632",
      "date": "2026-08-09",
      "epss": "0.0033",
      "percentile": "0.25487"
    },
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-43632\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-08-08T02:09:08.150856Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-08-08T02:09:14.121Z\"}}], \"cna\": {\"tags\": [\"x_open-source\"], \"title\": \"llama.cpp b7492\\u2013b9060 Use-After-Free in Tokenization Endpoints\", \"source\": {\"discovery\": \"EXTERNAL\"}, \"credits\": [{\"lang\": \"en\", \"type\": \"finder\", \"value\": \"Vladimir Tokarev (@G1ND1L4) - Vulnerability Research Tech Lead, Cyera\"}, {\"lang\": \"en\", \"type\": \"finder\", \"value\": \"Ofek Itach (@ofekitach) - Security Research Team Lead, Cyera\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV4_0\": {\"Safety\": \"NOT_DEFINED\", \"version\": \"4.0\", \"Recovery\": \"NOT_DEFINED\", \"baseScore\": 9.2, \"Automatable\": \"NOT_DEFINED\", \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"valueDensity\": \"NOT_DEFINED\", \"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\", \"exploitMaturity\": \"NOT_DEFINED\", \"providerUrgency\": \"NOT_DEFINED\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"attackRequirements\": \"PRESENT\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"HIGH\", \"vulnerabilityResponseEffort\": \"NOT_DEFINED\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 8.1, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}, \"scenarios\": [{\"lang\": \"en\", \"value\": \"GENERAL\"}]}], \"affected\": [{\"vendor\": \"ggml-org\", \"product\": \"llama.cpp\", \"versions\": [{\"status\": \"affected\", \"version\": \"b7492\", \"versionType\": \"custom\", \"lessThanOrEqual\": \"b9060\"}], \"defaultStatus\": \"affected\"}], \"datePublic\": \"2026-05-06T00:00:00.000Z\", \"references\": [{\"url\": \"https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches\", \"tags\": [\"mitigation\"]}, {\"url\": \"https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints\", \"tags\": [\"third-party-advisory\"]}], \"x_generator\": {\"engine\": \"vulncheck\"}, \"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.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-416\", \"description\": \"Use After Free\"}, {\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-367\", \"description\": \"Time-of-check Time-of-use (TOCTOU) Race Condition\"}]}], \"providerMetadata\": {\"orgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"shortName\": \"VulnCheck\", \"dateUpdated\": \"2026-08-07T19:06:44.455Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-43632\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-08T02:09:18.676Z\", \"dateReserved\": \"2026-05-01T18:22:45.641Z\", \"assignerOrgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"datePublished\": \"2026-08-06T15:53:19.379Z\", \"assignerShortName\": \"VulnCheck\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Detection rules are retrieved from Rulezet.