« Volver al listado

CVE-2025-6920

Estado: AnalizadaMedia (5.3)—

A flaw was found in the authentication enforcement mechanism of a model inference API in ai-inference-server. All /v1/* endpoints are expected to enforce API key validation. However, the POST /invocations endpoint failed to do so, resulting in an authentication bypass. This vulnerability allows unauthorized users to access the same inference features available on protected endpoints, potentially exposing sensitive functionality or allowing unintended access to backend resources.

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)

Redhat — AI Inference Server

CWE

Referencias

JSON original (NVD)

Mostrar
{
  "id": "CVE-2025-6920",
  "cveTags": [],
  "metrics": {
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2025-6920",
          "role": "CISA Coordinator",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "version": "2.0.3",
          "timestamp": "2025-07-01T13:30:12.685492Z"
        }
      }
    ],
    "cvssMetricV31": [
      {
        "type": "Secondary",
        "source": "secalert@redhat.com",
        "cvssData": {
          "scope": "UNCHANGED",
          "version": "3.1",
          "baseScore": 5.3,
          "attackVector": "NETWORK",
          "baseSeverity": "MEDIUM",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N",
          "integrityImpact": "NONE",
          "userInteraction": "NONE",
          "attackComplexity": "LOW",
          "availabilityImpact": "NONE",
          "privilegesRequired": "NONE",
          "confidentialityImpact": "LOW"
        },
        "impactScore": 1.4,
        "exploitabilityScore": 3.9
      }
    ]
  },
  "affected": [
    {
      "source": "secalert@redhat.com",
      "affectedData": [
        {
          "cpes": [
            "cpe:/a:redhat:ai_inference_server:3"
          ],
          "vendor": "Red Hat",
          "product": "Red Hat AI Inference Server",
          "packageName": "rhaiis/vllm-cuda-rhel9",
          "collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
          "defaultStatus": "affected"
        },
        {
          "cpes": [
            "cpe:/a:redhat:ai_inference_server:3"
          ],
          "vendor": "Red Hat",
          "product": "Red Hat AI Inference Server",
          "packageName": "rhaiis/vllm-rocm-rhel9",
          "collectionURL": "https://access.redhat.com/downloads/content/package-browser/",
          "defaultStatus": "affected"
        }
      ]
    }
  ],
  "published": "2025-07-01T14:15:41.690",
  "references": [
    {
      "url": "https://access.redhat.com/security/cve/CVE-2025-6920",
      "tags": [
        "Vendor Advisory"
      ],
      "source": "secalert@redhat.com"
    },
    {
      "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2375522",
      "tags": [
        "Issue Tracking",
        "Vendor Advisory"
      ],
      "source": "secalert@redhat.com"
    }
  ],
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "type": "Secondary",
      "source": "secalert@redhat.com",
      "description": [
        {
          "lang": "en",
          "value": "CWE-306"
        }
      ]
    }
  ],
  "descriptions": [
    {
      "lang": "en",
      "value": "A flaw was found in the authentication enforcement mechanism of a model inference API in ai-inference-server. All /v1/* endpoints are expected to enforce API key validation. However, the POST /invocations endpoint failed to do so, resulting in an authentication bypass. This vulnerability allows unauthorized users to access the same inference features available on protected endpoints, potentially exposing sensitive functionality or allowing unintended access to backend resources."
    },
    {
      "lang": "es",
      "value": "Se detectó una falla en el mecanismo de aplicación de la autenticación de una API de inferencia de modelos en ai-inference-server. Se espera que todos los endpoints /v1/* apliquen la validación de la clave API. Sin embargo, el endpoint POST /invocations no lo hizo, lo que resultó en una omisión de la autenticación. Esta vulnerabilidad permite a usuarios no autorizados acceder a las mismas funciones de inferencia disponibles en endpoints protegidos, lo que podría exponer funcionalidades sensibles o permitir el acceso no deseado a recursos del backend."
    }
  ],
  "lastModified": "2026-06-17T10:02:52.403",
  "configurations": [
    {
      "nodes": [
        {
          "negate": false,
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:redhat:ai_inference_server:-:*:*:*:*:*:*:*",
              "vulnerable": true,
              "matchCriteriaId": "C7E705EE-0973-438E-A35F-3A774ACADF67"
            }
          ],
          "operator": "OR"
        }
      ]
    }
  ],
  "sourceIdentifier": "secalert@redhat.com"
}