CVE-2025-65720

Estado: Pendiente de análisisCrítica (9.8)—

An issue in Open Source GPT Researcher v3.3.7 allows attackers to execute arbitrary commands on a victim system via user interaction with a crafted HTML page.

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: 0.89%
Percentil entre todas las CVEs puntuadas: 58
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.

ExplotaciónT1190 Exploit Public-Facing Applicationinitial access60 %
Impacto principalT1059 Command and Scripting Interpreterexecution55 %

Inferido por reglas deterministas a partir del vector CVSS y la CWE. Solo orientativo.

🛡️ 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.

Open Source GPT Researcher — GPT Researcher^AI

CWE

CWE-77

Referencias

JSON original (NVD)

Mostrar

{
  "id": "CVE-2025-65720",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2025-65720",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-07-16T18:11:53.845478Z"
        }
      }
    ],
    "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": "2026-07-15T22:16:45.417",
  "references": [
    {
      "url": "https://github.com/assafelovic/gpt-researcher",
      "source": "cve@mitre.org"
    },
    {
      "url": "https://www.ox.security/blog/gpt-researcher-remote-code-execution",
      "source": "cve@mitre.org"
    },
    {
      "url": "https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/",
      "source": "cve@mitre.org"
    }
  ],
  "vulnStatus": "Awaiting Analysis",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
      "description": [
        {
          "lang": "en",
          "value": "CWE-77"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "An issue in Open Source GPT Researcher v3.3.7 allows attackers to execute arbitrary commands on a victim system via user interaction with a crafted HTML page."
    },
    {
      "lang": "es",
      "value": "Un problema en Open Source GPT Researcher v3.3.7 permite a los atacantes ejecutar comandos arbitrarios en un sistema víctima mediante la interacción del usuario con una página HTML manipulada."
    }
  ],
  "lastModified": "2026-10-05T18:10:00.200",
  "sourceIdentifier": "cve@mitre.org"
}