CVE-2025-52566 (GCVE-0-2025-52566)
Vulnerability from cvelistv5
Published
2025-06-24 03:21
Modified
2025-06-24 21:49
Severity ?
8.6 (High) - CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
CWE
  • CWE-119 - Improper Restriction of Operations within the Bounds of a Memory Buffer
  • CWE-195 - Signed to Unsigned Conversion Error
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp's tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.
References
Impacted products
Vendor Product Version
ggml-org llama.cpp Version: < b5721
 Create a notification for this product.
Show details on NVD website

To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-52566",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-06-24T21:49:17.452816Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-06-24T21:49:53.200Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "llama.cpp",
          "vendor": "ggml-org",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c b5721"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp\u0027s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "LOCAL",
            "availabilityImpact": "HIGH",
            "baseScore": 8.6,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-119",
              "description": "CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer",
              "lang": "en",
              "type": "CWE"
            }
          ]
        },
        {
          "descriptions": [
            {
              "cweId": "CWE-195",
              "description": "CWE-195: Signed to Unsigned Conversion Error",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2025-06-24T03:21:19.009Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx"
        },
        {
          "name": "https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af"
        }
      ],
      "source": {
        "advisory": "GHSA-7rxv-5jhh-j6xx",
        "discovery": "UNKNOWN"
      },
      "title": "llama.cpp tokenizer signed vs. unsigned heap overflow"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-52566",
    "datePublished": "2025-06-24T03:21:19.009Z",
    "dateReserved": "2025-06-18T03:55:52.036Z",
    "dateUpdated": "2025-06-24T21:49:53.200Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2025-52566\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2025-06-24T04:15:46.967\",\"lastModified\":\"2025-06-26T18:58:14.280\",\"vulnStatus\":\"Awaiting Analysis\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp\u0027s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.\"},{\"lang\":\"es\",\"value\":\"llama.cpp es una inferencia de varios modelos LLM en C/C++. Antes de la versi\u00f3n b5721, se produc\u00eda un desbordamiento de enteros con signo y sin signo en la implementaci\u00f3n del tokenizador de llama.cpp (llama_vocab::tokenize) (src/llama-vocab.cpp:3036), lo que provocaba un comportamiento no deseado al comparar el tama\u00f1o de copia de tokens. Esto permit\u00eda el desbordamiento del mont\u00f3n del motor de inferencia de llama.cpp con una entrada de texto cuidadosamente manipulada durante el proceso de tokenizaci\u00f3n. Este problema se ha corregido en la versi\u00f3n b5721.\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H\",\"baseScore\":8.6,\"baseSeverity\":\"HIGH\",\"attackVector\":\"LOCAL\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":1.8,\"impactScore\":6.0}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-119\"},{\"lang\":\"en\",\"value\":\"CWE-195\"}]}],\"references\":[{\"url\":\"https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2025-52566\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2025-06-24T21:49:17.452816Z\"}}}], \"references\": [{\"url\": \"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2025-06-24T21:49:47.523Z\"}}], \"cna\": {\"title\": \"llama.cpp tokenizer signed vs. unsigned heap overflow\", \"source\": {\"advisory\": \"GHSA-7rxv-5jhh-j6xx\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"CHANGED\", \"version\": \"3.1\", \"baseScore\": 8.6, \"attackVector\": \"LOCAL\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"ggml-org\", \"product\": \"llama.cpp\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c b5721\"}]}], \"references\": [{\"url\": \"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx\", \"name\": \"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-7rxv-5jhh-j6xx\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af\", \"name\": \"https://github.com/ggml-org/llama.cpp/commit/dd6e6d0b6a4bbe3ebfc931d1eb14db2f2b1d70af\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp\u0027s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-119\", \"description\": \"CWE-119: Improper Restriction of Operations within the Bounds of a Memory Buffer\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-195\", \"description\": \"CWE-195: Signed to Unsigned Conversion Error\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2025-06-24T03:21:19.009Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2025-52566\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2025-06-24T21:49:53.200Z\", \"dateReserved\": \"2025-06-18T03:55:52.036Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2025-06-24T03:21:19.009Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.1"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




Sightings

Author Source Type Date

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
  • Confirmed: The vulnerability is confirmed from an analyst perspective.
  • Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
  • Patched: This vulnerability was successfully patched by the user reporting the sighting.
  • Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
  • Not confirmed: The user expresses doubt about the veracity of the vulnerability.
  • Not patched: This vulnerability was not successfully patched by the user reporting the sighting.