« Volver al listado

CVE-2025-67729

Estado: AnalizadaAlta (8.8)—

LMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weights_only=True parameter when loading model checkpoint files. This allows an attacker to execute arbitrary code on the victim's machine when they load a malicious .bin or .pt model file. This issue has been patched in version 0.11.1.

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 cargar archivo malicioso .bin/.pt. Deserialization insegura (CWE-502) permite ejecución arbitraria de código al abrir el fichero preparado.

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

Restrict Web-Based ContentPrivileged Account ManagementLimit Software InstallationExecution PreventionBehavior Prevention on EndpointDisable or Remove Feature or Program

Tecnologías afectadas (1)

Internlm — Lmdeploy

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2025-67729",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2025-67729",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2025-12-26T22:00:24.502538Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 8.8,
          "attackVector": "NETWORK",
          "baseSeverity": "HIGH",
          "vectorString": "CVSS:3.1/AV:N/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": 2.8
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "InternLM",
          "product": "lmdeploy",
          "versions": [
            {
              "status": "affected",
              "version": "< 0.11.1"
            }
          ]
        }
      ]
    }
  ],
  "published": "2025-12-26T22:15:52.437",
  "references": [
    {
      "url": "https://github.com/InternLM/lmdeploy/commit/eb04b4281c5784a5cff5ea639c8f96b33b3ae5ee",
      "tags": [
        "Patch"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh",
      "tags": [
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/InternLM/lmdeploy/security/advisories/GHSA-9pf3-7rrr-x5jh",
      "tags": [
        "Vendor Advisory"
      ],
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-502"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "LMDeploy is a toolkit for compressing, deploying, and serving LLMs. Prior to version 0.11.1, an insecure deserialization vulnerability exists in lmdeploy where torch.load() is called without the weights_only=True parameter when loading model checkpoint files. This allows an attacker to execute arbitrary code on the victim's machine when they load a malicious .bin or .pt model file. This issue has been patched in version 0.11.1."
    },
    {
      "lang": "es",
      "value": "LMDeploy es un conjunto de herramientas para comprimir, desplegar y servir LLMs. Antes de la versión 0.11.1, existe una vulnerabilidad de deserialización insegura en lmdeploy donde se llama a torch.load() sin el parámetro weights_only=True al cargar archivos de puntos de control del modelo. Esto permite a un atacante ejecutar código arbitrario en la máquina de la víctima cuando cargan un archivo de modelo malicioso .bin o .pt. Este problema ha sido parcheado en la versión 0.11.1."
    }
  ],
  "lastModified": "2026-10-05T19:10:00.210",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:internlm:lmdeploy:*:*:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "7671A435-D4FF-42D3-B8BD-D530FE24F13B",
              "versionEndExcluding": "0.11.1"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}