« Volver al listado

CVE-2026-33298

Estado: AnalizadaAlta (7.8)—

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.

CVSS

Probabilidad de explotación (EPSS)

EPSS (Exploit Prediction Scoring System, de FIRST) estima la probabilidad de que una vulnerabilidad sea explotada en 30 días. Complementa a CVSS (impacto) y a CISA KEV (explotación confirmada).

🎯 Técnicas ATT&CK

Cómo se explota esta vulnerabilidad y qué consigue el atacante, en el lenguaje de MITRE ATT&CK.

Requiere interacción del usuario (UI:R) para abrir un archivo GGUF preparado localmente, causando ejecución de código arbitrario mediante corrupción de memoria heap (integer overflow en ggml_nbytes).

Inferido por nuestro agente de análisis a partir de la descripción oficial, el vector CVSS y la CWE, y comprobado por un supervisor. Puede contener errores.

🛡️ Mitigaciones ATT&CK que cubren estas técnicas

Execution PreventionApplication Isolation and SandboxingExploit ProtectionUpdate SoftwareThreat Intelligence ProgramRestrict Web-Based Content

Tecnologías afectadas (1)

Ggml — Llama.cpp

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2026-33298",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-33298",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-03-24T00:00:00+00:00"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 7.8,
          "attackVector": "LOCAL",
          "baseSeverity": "HIGH",
          "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
          "integrityImpact": "HIGH",
          "userInteraction": "REQUIRED",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "HIGH"
        },
        "impactScore": 5.9,
        "exploitabilityScore": 1.8
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "ggml-org",
          "product": "llama.cpp",
          "versions": [
            {
              "status": "affected",
              "version": "< b7824"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-03-24T01:17:01.870",
  "references": [
    {
      "url": "https://github.com/ggml-org/llama.cpp/releases/tag/b7824",
      "tags": [
        "Release Notes"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-96jg-mvhq-q7q7",
      "tags": [
        "Exploit",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-122"
        },
        {
          "lang": "en",
          "value": "CWE-190"
        }
      ]
    }
  ],
  "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 función `ggml_nbytes` permite a un atacante eludir la validación de memoria al crear un archivo GGUF con dimensiones de tensor específicas. Esto hace que `ggml_nbytes` devuelva un tamaño significativamente menor al requerido (por ejemplo, 4MB en lugar de Exabytes), lo que lleva a un desbordamiento de búfer basado en montículo cuando la aplicación procesa posteriormente el tensor. Esta vulnerabilidad permite una posible ejecución remota de código (RCE) a través de corrupción de memoria. b7824 contiene una corrección."
    }
  ],
  "lastModified": "2026-06-17T10:37:16.580",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "471181FC-F68E-43C2-AC26-06D790AEE75F",
              "versionEndExcluding": "b7824"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}