FKIE_CVE-2026-33298

Vulnerability from fkie_nvd - Published: 2026-03-24 01:17 - Updated: 2026-06-17 10:37
Severity
7.8 (High) - CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Summary
llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix.
References
security-advisories@github.comhttps://github.com/ggml-org/llama.cpp/releases/tag/b7824Release Notes
security-advisories@github.comhttps://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7Exploit, Vendor Advisory
Impacted products
Vendor Product Version
ggml llama.cpp *
To clipboard 

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "llama.cpp",
          "vendor": "ggml-org",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c b7824"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "471181FC-F68E-43C2-AC26-06D790AEE75F",
              "versionEndExcluding": "b7824",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "llama.cpp is an inference of several LLM models in C/C++. Prior to b7824, an integer overflow vulnerability in the `ggml_nbytes` function allows an attacker to bypass memory validation by crafting a GGUF file with specific tensor dimensions. This causes `ggml_nbytes` to return a significantly smaller size than required (e.g., 4MB instead of Exabytes), leading to a heap-based buffer overflow when the application subsequently processes the tensor. This vulnerability allows potential Remote Code Execution (RCE) via memory corruption. b7824 contains a fix."
    },
    {
      "lang": "es",
      "value": "llama.cpp es una inferencia de varios modelos LLM en C/C++. Antes de b7824, una vulnerabilidad de desbordamiento de entero en la funci\u00f3n `ggml_nbytes` permite a un atacante eludir la validaci\u00f3n de memoria al crear un archivo GGUF con dimensiones de tensor espec\u00edficas. Esto hace que `ggml_nbytes` devuelva un tama\u00f1o significativamente menor al requerido (por ejemplo, 4MB en lugar de Exabytes), lo que lleva a un desbordamiento de b\u00fafer basado en mont\u00edculo cuando la aplicaci\u00f3n procesa posteriormente el tensor. Esta vulnerabilidad permite una posible ejecuci\u00f3n remota de c\u00f3digo (RCE) a trav\u00e9s de corrupci\u00f3n de memoria. b7824 contiene una correcci\u00f3n."
    }
  ],
  "id": "CVE-2026-33298",
  "lastModified": "2026-06-17T10:37:16.580",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "LOCAL",
          "availabilityImpact": "HIGH",
          "baseScore": 7.8,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "REQUIRED",
          "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 1.8,
        "impactScore": 5.9,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-33298",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-03-24T00:00:00+00:00",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-03-24T01:17:01.870",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Release Notes"
      ],
      "url": "https://github.com/ggml-org/llama.cpp/releases/tag/b7824"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Exploit",
        "Vendor Advisory"
      ],
      "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-122"
        },
        {
          "lang": "en",
          "value": "CWE-190"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}



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.



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.