CVE-2026-26020

Estado: AnalizadaCrítica (9.4)—

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to 0.6.48, an authenticated user could achieve Remote Code Execution (RCE) on the backend server by embedding a disabled block inside a graph. The BlockInstallationBlock — a development tool capable of writing and importing arbitrary Python code — was marked disabled=True, but graph validation did not enforce this flag. This allowed any authenticated user to bypass the restriction by including the block as a node in a graph, rather than calling the block's execution endpoint directly (which did enforce the flag). This vulnerability is fixed in 0.6.48.

CVSS

Versión: 4.0
Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Puntuación base: 9.4

Probabilidad de explotación (EPSS)

Probabilidad de explotación en los próximos 30 días: 0.88%
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.

ExplotaciónT1210 Exploitation of Remote Serviceslateral movement95 %
Impacto principalT1059 Command and Scripting Interpreterexecution90 %

Usuario autenticado ejecuta código Python arbitrario en servidor backend mediante bloque deshabilitado en grafo, omitiendo validación. AV:N, PR:L, RCE explícita confirmada en descripción.

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 Disable or Remove Feature or Program Vulnerability Scanning Threat Intelligence Program Restrict Web-Based Content Network Segmentation

Tecnologías afectadas (1)

Agpt — Autogpt Platform

CWE

CWE-285

Referencias

JSON original (NVD)

Mostrar

{
  "id": "CVE-2026-26020",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-26020",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-02-12T21:03:05.471651Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Primary",
        "source": "nvd@nist.gov",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 8.8,
          "attackVector": "NETWORK",
          "baseSeverity": "HIGH",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
          "integrityImpact": "HIGH",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "LOW",
          "confidentialityImpact": "HIGH"
        },
        "impactScore": 5.9,
        "exploitabilityScore": 2.8
      }
    ],
    "cvssMetricV40": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "Safety": "NOT_DEFINED",
          "version": "4.0",
          "Recovery": "NOT_DEFINED",
          "baseScore": 9.4,
          "Automatable": "NOT_DEFINED",
          "attackVector": "NETWORK",
          "baseSeverity": "CRITICAL",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
          "exploitMaturity": "NOT_DEFINED",
          "providerUrgency": "NOT_DEFINED",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "attackRequirements": "NONE",
          "privilegesRequired": "LOW",
          "subIntegrityImpact": "HIGH",
          "vulnIntegrityImpact": "HIGH",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "subAvailabilityImpact": "HIGH",
          "vulnAvailabilityImpact": "HIGH",
          "availabilityRequirement": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "subConfidentialityImpact": "HIGH",
          "vulnConfidentialityImpact": "HIGH",
          "confidentialityRequirement": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "vulnerabilityResponseEffort": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED"
        }
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "Significant-Gravitas",
          "product": "AutoGPT",
          "versions": [
            {
              "status": "affected",
              "version": "< 0.6.48"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-02-12T21:16:03.500",
  "references": [
    {
      "url": "https://github.com/Significant-Gravitas/AutoGPT/commit/062fe1aa709217136b896c8b950e0f04435afb32",
      "tags": [
        "Patch"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.48",
      "tags": [
        "Release Notes"
      ],
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4crw-9p35-9x54",
      "tags": [
        "Mitigation",
        "Vendor Advisory"
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-285"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to 0.6.48, an authenticated user could achieve Remote Code Execution (RCE) on the backend server by embedding a disabled block inside a graph. The BlockInstallationBlock — a development tool capable of writing and importing arbitrary Python code — was marked disabled=True, but graph validation did not enforce this flag. This allowed any authenticated user to bypass the restriction by including the block as a node in a graph, rather than calling the block's execution endpoint directly (which did enforce the flag). This vulnerability is fixed in 0.6.48."
    },
    {
      "lang": "es",
      "value": "AutoGPT es una plataforma que permite a los usuarios crear, desplegar y gestionar agentes de inteligencia artificial continuos que automatizan flujos de trabajo complejos. Antes de la versión 0.6.48, un usuario autenticado podría lograr Ejecución Remota de Código (RCE) en el servidor de backend al incrustar un bloque deshabilitado dentro de un grafo. El BlockInstallationBlock — una herramienta de desarrollo capaz de escribir e importar código Python arbitrario — estaba marcado como disabled=True, pero la validación del grafo no aplicaba esta bandera. Esto permitía a cualquier usuario autenticado eludir la restricción al incluir el bloque como un nodo en un grafo, en lugar de llamar directamente al punto final de ejecución del bloque (que sí aplicaba la bandera). Esta vulnerabilidad está corregida en la versión 0.6.48."
    }
  ],
  "lastModified": "2026-06-17T10:25:36.717",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:agpt:autogpt_platform:*:beta:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "FD36801A-02E5-4B2A-B721-2105F207C9A3",
              "versionEndExcluding": "0.6.48"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "security-advisories@github.com"
}