« Volver al listado

CVE-2026-45023

Estado: AplazadaMedia (5.4)—

AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.59, POST /api/blocks/{block_id}/execute endpoint executes blocks without consuming any credits, regardless of the user's balance. The credit check that exists in the graph execution path (manager.py) is never reached when blocks are called directly via the external API, allowing unlimited free execution of all blocks. This vulnerability is fixed in 0.6.59.

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).

Tecnologías afectadas (1)

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

Autogpt — AutogptAI

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2026-45023",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-45023",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-05-29T13:36:55.269880Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 5.4,
          "attackVector": "NETWORK",
          "baseSeverity": "MEDIUM",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:L",
          "integrityImpact": "LOW",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "LOW",
          "privilegesRequired": "LOW",
          "confidentialityImpact": "NONE"
        },
        "impactScore": 2.5,
        "exploitabilityScore": 2.8
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "Significant-Gravitas",
          "product": "AutoGPT",
          "versions": [
            {
              "status": "affected",
              "version": "< 0.6.59"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-05-28T22:17:00.080",
  "references": [
    {
      "url": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-8pjg-mfqm-vrhr",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-8pjg-mfqm-vrhr",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ],
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-770"
        },
        {
          "lang": "en",
          "value": "CWE-841"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.59, POST /api/blocks/{block_id}/execute endpoint executes blocks without consuming any credits, regardless of the user's balance. The credit check that exists in the graph execution path (manager.py) is never reached when blocks are called directly via the external API, allowing unlimited free execution of all blocks. This vulnerability is fixed in 0.6.59."
    },
    {
      "lang": "es",
      "value": "AutoGPT es una plataforma de automatización de flujos de trabajo para crear, desplegar y gestionar agentes de inteligencia artificial continuos. Antes de la versión 0.6.59, el endpoint POST /API/blocks/{block_id}/execute ejecuta bloques sin consumir ningún crédito, independientemente del saldo del usuario. La verificación de crédito que existe en la ruta de ejecución del grafo (manager.py) nunca se alcanza cuando los bloques se llaman directamente a través de la API externa, permitiendo la ejecución gratuita ilimitada de todos los bloques. Esta vulnerabilidad se corrige en la versión 0.6.59."
    }
  ],
  "lastModified": "2026-07-21T10:10:00.103",
  "sourceIdentifier": "security-advisories@github.com"
}