{
  "affected": [
    {
      "ranges": [
        {
          "database_specific": {
            "cpe": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
            "extracted_events": [
              {
                "introduced": "b7492"
              },
              {
                "last_affected": "b9060"
              }
            ],
            "source": "CPE_RANGE"
          },
          "events": [
            {
              "introduced": "ddcb75dd8ac42dc23eb84f13bb17670fe9f2d49b"
            },
            {
              "last_affected": "ad092246587b16299291056a78bf6f73f636f114"
            }
          ],
          "repo": "https://github.com/ggml-org/llama.cpp",
          "type": "GIT"
        }
      ]
    }
  ],
  "database_specific": {
    "cna_assigner": "VulnCheck",
    "cwe_ids": [
      "CWE-367",
      "CWE-416"
    ],
    "osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/43xxx/CVE-2026-43632.json",
    "unresolved_ranges": [
      {
        "extracted_events": [
          {
            "introduced": "b7492"
          },
          {
            "last_affected": "b9060"
          }
        ],
        "source": "AFFECTED_FIELD"
      },
      {
        "extracted_events": [
          {
            "introduced": "b7492"
          },
          {
            "last_affected": "b9060"
          }
        ],
        "source": "CPE_FIELD"
      },
      {
        "extracted_events": [
          {
            "introduced": "b7492"
          }
        ],
        "source": "DESCRIPTION"
      }
    ]
  },
  "details": "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.",
  "id": "CVE-2026-43632",
  "modified": "2026-09-23T03:30:47.583193912Z",
  "published": "2026-08-06T15:53:19.379Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/43xxx/CVE-2026-43632.json"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-43632"
    },
    {
      "type": "ADVISORY",
      "url": "https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-in-tokenization-endpoints"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches"
    }
  ],
  "schema_version": "1.9.0",
  "severity": [
    {
      "score": "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",
      "type": "CVSS_V4"
    }
  ],
  "summary": "llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints"
}