CVE-2026-33234

{
  "id": "CVE-2026-33234",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-33234",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-05-19T16:28:15.558069Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "security-advisories@github.com",
        "cvssData": {
          "scope": "CHANGED",
          "version": "3.1",
          "baseScore": 5,
          "attackVector": "NETWORK",
          "baseSeverity": "MEDIUM",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:L/I:N/A:N",
          "integrityImpact": "NONE",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "NONE",
          "privilegesRequired": "LOW",
          "confidentialityImpact": "LOW"
        },
        "impactScore": 1.4,
        "exploitabilityScore": 3.1
      }
    ]
  },
  "affected": [
    {
      "source": "security-advisories@github.com",
      "affectedData": [
        {
          "vendor": "Significant-Gravitas",
          "product": "AutoGPT",
          "versions": [
            {
              "status": "affected",
              "version": ">= 0.1.0, < 0.6.52"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-05-19T02:16:16.010",
  "references": [
    {
      "url": "https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.52",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4jwj-6mg5-wrwf",
      "source": "security-advisories@github.com"
    },
    {
      "url": "https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4jwj-6mg5-wrwf",
      "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0"
    }
  ],
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security-advisories@github.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-918"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.1.0 through 0.6.51,  SendEmailBlock in autogpt_platform/backend/backend/blocks/email_block.py accepts a user-supplied smtp_server (string) and smtp_port (integer) as per-execution block inputs, then passes them directly to Python's smtplib.SMTP() to open a raw TCP connection with no IP address validation. This completely bypasses the platform's hardened SSRF protections in backend/util/request.py — the validate_url_host() function and BLOCKED_IP_NETWORKS blocklist that every other block uses to block connections to private, loopback, link-local, and cloud metadata addresses. An authenticated user on a shared AutoGPT deployment can use this to perform non-blind internal network port scanning and service fingerprinting: smtplib reads the target's TCP banner on connect and embeds it in the exception message, which is persisted as user-visible block output via the execution framework. This issue has been fixed in version 0.6.52."
    },
    {
      "lang": "es",
      "value": "AutoGPT es una plataforma de automatización de flujos de trabajo para crear, desplegar y gestionar agentes de inteligencia artificial continuos. En las versiones 0.1.0 a 0.6.51, SendEmailBlock en autogpt_platform/backend/backend/blocks/email_block.py acepta un smtp_server (cadena de texto) y un smtp_port (entero) proporcionados por el usuario como entradas de bloque por ejecución, luego los pasa directamente a smtplib.SMTP() de Python para abrir una conexión TCP sin procesar sin validación de dirección IP. Esto elude completamente las protecciones SSRF reforzadas de la plataforma en backend/util/request.py - la función validate_url_host() y la lista de bloqueo BLOCKED_IP_NETWORKS que todos los demás bloques utilizan para bloquear conexiones a direcciones privadas, de bucle invertido, de enlace local y de metadatos en la nube. Un usuario autenticado en una implementación compartida de AutoGPT puede usar esto para realizar escaneo de puertos de red interno no ciego y huellas digitales de servicios: smtplib lee el banner TCP del objetivo al conectarse y lo incrusta en el mensaje de excepción, que se persiste como salida de bloque visible para el usuario a través del framework de ejecución. Este problema ha sido solucionado en la versión 0.6.52."
    }
  ],
  "lastModified": "2026-07-24T13:10:00.223",
  "sourceIdentifier": "security-advisories@github.com"
}