CVE-2026-27940

Estado: AnalizadaAlta (7.8)—

llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.

CVSS

Versión: 3.1
Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Puntuación base: 7.8

Probabilidad de explotación (EPSS)

Probabilidad de explotación en los próximos 30 días: 0.18%
Percentil entre todas las CVEs puntuadas: 7
Fecha de la puntuación: 6/10/2026

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.

ExplotaciónT1203 Exploitation for Client Executionexecution90 %
Impacto principalT1059 Command and Scripting Interpreterexecution85 %
Impacto secundarioT1068 Exploitation for Privilege Escalationprivilege escalation75 %

Vector AV:L/UI:R indica ejecución en cliente (abrir archivo GGUF preparado). Integer overflow → heap overflow → RCE. Acceso local con interacción del usuario = T1203.

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 Prevention Application Isolation and Sandboxing Exploit Protection Update Software Threat Intelligence Program Restrict Web-Based Content

Tecnologías afectadas (1)

Ggml — Llama.cpp

CWE

CWE-122, CWE-190

Referencias

https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v

JSON original (NVD)

Mostrar

{
  "id": "CVE-2026-27940",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-27940",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-03-12T00:00:00+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": "< b8146"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-03-12T17:16:49.920",
  "references": [
    {
      "url": "https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v",
      "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 b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146."
    },
    {
      "lang": "es",
      "value": "llama.cpp es una inferencia de varios modelos LLM en C/C++. Antes de b8146, la gguf_init_from_file_impl() en gguf.cpp es vulnerable a un desbordamiento de entero, lo que lleva a una asignación de memoria heap de tamaño insuficiente. El uso de la posterior fread() escribe más de 528 bytes de datos controlados por el atacante más allá del límite del búfer. Esto es un bypass de un error similar en el mismo archivo - CVE-2025-53630, pero la corrección pasó por alto algunas áreas. Esta vulnerabilidad está corregida en b8146."
    }
  ],
  "lastModified": "2026-06-17T10:27:56.667",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "4948FEA7-D4C9-48A1-BF6A-5A17D230E9D7",
              "versionEndExcluding": "b8146"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}