« Back to list

CVE-2026-0599

Status: DeferredHigh (7.5)—

A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU overutilization.

Read full descriptionShow less

The vulnerability is triggered even if the request is later rejected for exceeding token limits. The default deployment configuration, which lacks memory usage limits and authentication, exacerbates the impact, potentially crashing the host machine. The issue is resolved in version 3.3.7.

CVSS

Exploitation probability (EPSS)

EPSS (Exploit Prediction Scoring System, FIRST) estimates how likely a vulnerability is to be exploited in the wild within 30 days. It complements CVSS (impact) and CISA KEV (confirmed exploitation).

🎯 ATT&CK techniques

How this vulnerability is exploited and what the attacker gains, in MITRE ATT&CK terms.

Vulnerabilidad remota sin autenticación en servicio expuesto (AV:N/PR:N/UI:N). CWE-400 y descripción indican DoS por agotamiento de recursos: saturación de ancho de banda, inflación de memoria y sobrecarga de CPU mediante fetches HTTP no acotadas.

Inferred by our analysis agent from the official description, CVSS vector and CWE, and checked by a supervisor. May contain errors.

🛡️ ATT&CK mitigations that cover these techniques

Affected technologies (1)

⚠ AI-inferred from the description — NVD hasn't analyzed this CVE yet, these aren't verified CPEs.

CWEs

References

Raw JSON (NVD)

Show
{
  "id": "CVE-2026-0599",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-0599",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "poc"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2026-02-02T12:48:08.191120Z"
        }
      }
    ],
    "cvssMetricV30": [
      {
        "type": "Secondary",
        "source": "security@huntr.dev",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.0",
          "baseScore": 7.5,
          "attackVector": "NETWORK",
          "baseSeverity": "HIGH",
          "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H",
          "integrityImpact": "NONE",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "NONE"
        },
        "impactScore": 3.6,
        "exploitabilityScore": 3.9
      }
    ]
  },
  "affected": [
    {
      "source": "security@huntr.dev",
      "affectedData": [
        {
          "vendor": "huggingface",
          "product": "huggingface/text-generation-inference",
          "versions": [
            {
              "status": "affected",
              "version": "unspecified",
              "lessThan": "3.3.7",
              "versionType": "custom"
            }
          ]
        }
      ]
    }
  ],
  "published": "2026-02-02T11:16:17.773",
  "references": [
    {
      "url": "https://github.com/huggingface/text-generation-inference/commit/24ee40d143d8d046039f12f76940a85886cbe152",
      "source": "security@huntr.dev"
    },
    {
      "url": "https://huntr.com/bounties/1d3f2085-666c-4441-b265-22f6f7d8d9cd",
      "source": "security@huntr.dev"
    }
  ],
  "vulnStatus": "Deferred",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "security@huntr.dev",
      "description": [
        {
          "lang": "en",
          "value": "CWE-400"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "A vulnerability in huggingface/text-generation-inference version 3.3.6 allows unauthenticated remote attackers to exploit unbounded external image fetching during input validation in VLM mode. The issue arises when the router scans inputs for Markdown image links and performs a blocking HTTP GET request, reading the entire response body into memory and cloning it before decoding. This behavior can lead to resource exhaustion, including network bandwidth saturation, memory inflation, and CPU overutilization. The vulnerability is triggered even if the request is later rejected for exceeding token limits. The default deployment configuration, which lacks memory usage limits and authentication, exacerbates the impact, potentially crashing the host machine. The issue is resolved in version 3.3.7."
    },
    {
      "lang": "es",
      "value": "Una vulnerabilidad en huggingface/text-generation-inference versión 3.3.6 permite a atacantes remotos no autenticados explotar la obtención ilimitada de imágenes externas durante la validación de entrada en modo VLM. El problema surge cuando el router escanea las entradas en busca de enlaces de imagen Markdown y realiza una solicitud HTTP GET bloqueante, leyendo todo el cuerpo de la respuesta en la memoria y clonándolo antes de decodificar. Este comportamiento puede llevar al agotamiento de recursos, incluyendo la saturación del ancho de banda de la red, la inflación de memoria y la sobreutilización de la CPU. La vulnerabilidad se activa incluso si la solicitud es posteriormente rechazada por exceder los límites de tokens. La configuración de despliegue predeterminada, que carece de límites de uso de memoria y autenticación, exacerba el impacto, pudiendo provocar el bloqueo de la máquina anfitriona. El problema está resuelto en la versión 3.3.7."
    }
  ],
  "lastModified": "2026-06-17T10:11:01.900",
  "sourceIdentifier": "security@huntr.dev"
}