CVE-2025-46059

Estado: AplazadaCrítica (9.8)—

langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code and compromise the application via a crafted email message. NOTE: this is disputed by the Supplier because the code-execution issue was introduced by user-written code that does not adhere to the LangChain security practices.

CVSS

Versión: 3.1
Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Puntuación base: 9.8

Probabilidad de explotación (EPSS)

Probabilidad de explotación en los próximos 30 días: 0.73%
Percentil entre todas las CVEs puntuadas: 53
Fecha de la puntuación: 5/10/2026

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.

ExplotaciónT1190 Exploit Public-Facing Applicationinitial access85 %
Impacto principalT1059 Command and Scripting Interpreterexecution80 %

Vulnerabilidad remota en componente GmailToolkit de LangChain expuesto a red (AV:N, PR:N, UI:N) que permite inyección indirecta de prompts (CWE-94) resultando en ejecución de código arbitrario. Vector CVSS crítico sin requerimientos previos.

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

Privileged Account Management Vulnerability Scanning Restrict Web-Based Content Network Segmentation Limit Software Installation Limit Access to Resource Over Network

Tecnologías afectadas (1)

⚠ Inferidas por IA a partir de la descripción — NVD aún no ha analizado esta CVE; no son CPE verificados.

Langchain — Langchain^AI

CWE

CWE-94

Referencias

JSON original (NVD)

Mostrar

{
  "id": "CVE-2025-46059",
  "cveTags": [
    {
      "tags": [
        "disputed"
      ],
      "sourceIdentifier": "cve@mitre.org"
    }
  ],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2025-46059",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2025-07-29T14:55:27.105160Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 9.8,
          "attackVector": "NETWORK",
          "baseSeverity": "CRITICAL",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
          "integrityImpact": "HIGH",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "HIGH"
        },
        "impactScore": 5.9,
        "exploitabilityScore": 3.9
      }
    ]
  },
  "affected": [
    {
      "source": "cve@mitre.org",
      "affectedData": [
        {
          "vendor": "n/a",
          "product": "n/a",
          "versions": [
            {
              "status": "affected",
              "version": "n/a"
            }
          ]
        }
      ]
    }
  ],
  "published": "2025-07-29T15:15:35.003",
  "references": [
    {
      "url": "https://github.com/Jr61-star/CVEs/blob/main/CVE-2025-46059.md",
      "source": "cve@mitre.org"
    },
    {
      "url": "https://github.com/langchain-ai/langchain-community/issues/217#issuecomment-3144824471",
      "source": "cve@mitre.org"
    },
    {
      "url": "https://github.com/langchain-ai/langchain/issues/30833",
      "source": "cve@mitre.org"
    },
    {
      "url": "https://python.langchain.com/docs/security/",
      "source": "cve@mitre.org"
    }
  ],
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "description": [
        {
          "lang": "en",
          "value": "CWE-94"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "langchain-ai v0.3.51 was discovered to contain an indirect prompt injection vulnerability in the GmailToolkit component. This vulnerability allows attackers to execute arbitrary code and compromise the application via a crafted email message. NOTE: this is disputed by the Supplier because the code-execution issue was introduced by user-written code that does not adhere to the LangChain security practices."
    },
    {
      "lang": "es",
      "value": "Se descubrió que langchain-ai v0.3.51 contenía una vulnerabilidad de inyección indirecta de mensajes en el componente GmailToolkit. Esta vulnerabilidad permite a los atacantes ejecutar código arbitrario y comprometer la aplicación mediante un mensaje de correo electrónico manipulado."
    }
  ],
  "lastModified": "2026-06-17T09:25:54.267",
  "sourceIdentifier": "cve@mitre.org"
}