Vulnerability-Lookup

CNVD-2024-46005

Vulnerability from cnvd - Published: 2024-11-26

Title

llama.cpp全局缓冲区溢出漏洞

Description

llama.cpp是一个多模态模型。 llama.cpp存在全局缓冲区溢出漏洞，攻击者可利用该漏洞导致内存数据泄露。

Severity

中

Patch Name

llama.cpp全局缓冲区溢出漏洞的补丁

Patch Description

llama.cpp是一个多模态模型。 llama.cpp存在全局缓冲区溢出漏洞，攻击者可利用该漏洞导致内存数据泄露。目前，供应商发布了安全公告及相关补丁信息，修复了此漏洞。

Formal description

厂商已发布了漏洞修复程序，请及时关注更新： https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b

Reference

https://nvd.nist.gov/vuln/detail/CVE-2024-42477

Impacted products

Name
llama.cpp llama.cpp <b3561

Show details on source website

JSON

To clipboard

{
  "cves": {
    "cve": {
      "cveNumber": "CVE-2024-42477",
      "cveUrl": "https://nvd.nist.gov/vuln/detail/CVE-2024-42477"
    }
  },
  "description": "llama.cpp\u662f\u4e00\u4e2a\u591a\u6a21\u6001\u6a21\u578b\u3002\n\nllama.cpp\u5b58\u5728\u5168\u5c40\u7f13\u51b2\u533a\u6ea2\u51fa\u6f0f\u6d1e\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u5bfc\u81f4\u5185\u5b58\u6570\u636e\u6cc4\u9732\u3002",
  "formalWay": "\u5382\u5546\u5df2\u53d1\u5e03\u4e86\u6f0f\u6d1e\u4fee\u590d\u7a0b\u5e8f\uff0c\u8bf7\u53ca\u65f6\u5173\u6ce8\u66f4\u65b0\uff1a\r\nhttps://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b",
  "isEvent": "\u901a\u7528\u8f6f\u786c\u4ef6\u6f0f\u6d1e",
  "number": "CNVD-2024-46005",
  "openTime": "2024-11-26",
  "patchDescription": "llama.cpp\u662f\u4e00\u4e2a\u591a\u6a21\u6001\u6a21\u578b\u3002\r\n\r\nllama.cpp\u5b58\u5728\u5168\u5c40\u7f13\u51b2\u533a\u6ea2\u51fa\u6f0f\u6d1e\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u5bfc\u81f4\u5185\u5b58\u6570\u636e\u6cc4\u9732\u3002\u76ee\u524d\uff0c\u4f9b\u5e94\u5546\u53d1\u5e03\u4e86\u5b89\u5168\u516c\u544a\u53ca\u76f8\u5173\u8865\u4e01\u4fe1\u606f\uff0c\u4fee\u590d\u4e86\u6b64\u6f0f\u6d1e\u3002",
  "patchName": "llama.cpp\u5168\u5c40\u7f13\u51b2\u533a\u6ea2\u51fa\u6f0f\u6d1e\u7684\u8865\u4e01",
  "products": {
    "product": "llama.cpp llama.cpp \u003cb3561"
  },
  "referenceLink": "https://nvd.nist.gov/vuln/detail/CVE-2024-42477",
  "serverity": "\u4e2d",
  "submitTime": "2024-08-20",
  "title": "llama.cpp\u5168\u5c40\u7f13\u51b2\u533a\u6ea2\u51fa\u6f0f\u6d1e"
}

CVE-2024-42477 (GCVE-0-2024-42477)

Vulnerability from cvelistv5 – Published: 2024-08-12 15:02 – Updated: 2024-08-13 14:07

Title

llama.cpp global-buffer-overflow in ggml_type_size

Summary

llama.cpp provides LLM inference in C/C++. The unsafe `type` member in the `rpc_tensor` structure can cause `global-buffer-overflow`. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561.

Severity

5.3 (Medium)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

SSVC

Exploitation: poc Automatable: yes Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2024-08-13 14:06 UTC

CWE

CWE-125 - Out-of-bounds Read

Assigner

GitHub_M mitre root

References

2 references

URL	Tags
https://github.com/ggerganov/llama.cpp/security/a…	x_refsource_CONFIRM
https://github.com/ggerganov/llama.cpp/commit/b72…	x_refsource_MISC

Impacted products

2 products

Vendor	Product	Version
ggerganov	llama.cpp	Affected: < b3561
ggerganov	llama.cpp	Affected: 0 , < b3561 (custom) cpe:2.3:a:ggerganov:llama.cpp::::::::

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "affected": [
          {
            "cpes": [
              "cpe:2.3:a:ggerganov:llama.cpp:*:*:*:*:*:*:*:*"
            ],
            "defaultStatus": "unknown",
            "product": "llama.cpp",
            "vendor": "ggerganov",
            "versions": [
              {
                "lessThan": "b3561",
                "status": "affected",
                "version": "0",
                "versionType": "custom"
              }
            ]
          }
        ],
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2024-42477",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2024-08-13T14:06:01.701592Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2024-08-13T14:07:30.334Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "llama.cpp",
          "vendor": "ggerganov",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c b3561"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "llama.cpp provides LLM inference in C/C++. The unsafe `type` member in the `rpc_tensor` structure can cause `global-buffer-overflow`. This vulnerability may lead to memory data leakage. The vulnerability is fixed in b3561."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 5.3,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "LOW",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-125",
              "description": "CWE-125: Out-of-bounds Read",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2024-08-12T15:02:40.980Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-mqp6-7pv6-fqjf",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/ggerganov/llama.cpp/security/advisories/GHSA-mqp6-7pv6-fqjf"
        },
        {
          "name": "https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/ggerganov/llama.cpp/commit/b72942fac998672a79a1ae3c03b340f7e629980b"
        }
      ],
      "source": {
        "advisory": "GHSA-mqp6-7pv6-fqjf",
        "discovery": "UNKNOWN"
      },
      "title": "llama.cpp global-buffer-overflow in ggml_type_size"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2024-42477",
    "datePublished": "2024-08-12T15:02:40.980Z",
    "dateReserved": "2024-08-02T14:13:04.616Z",
    "dateUpdated": "2024-08-13T14:07:30.334Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.1"
}

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.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.