CVE-2026-22807 (GCVE-0-2026-22807)

Vulnerability from cvelistv5 – Published: 2026-01-21 21:13 – Updated: 2026-06-30 12:06
VLAI
Title
vLLM affected by RCE via auto_map dynamic module loading during model initialization
Summary
vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.
Severity
8.8 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
SSVC
Exploitation: none Automatable: no Technical Impact: total
CISA Coordinator (v2.0.3)
CWE
  • CWE-94 - Improper Control of Generation of Code ('Code Injection')
Assigner
References
Impacted products
Show details on NVD website
To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-22807",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-01-22T15:11:00.640100Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-01-22T16:50:33.696Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      },
      {
        "affected": [
          {
            "cpes": [
              "cpe:/a:redhat:ai_inference_server:3.2::el9"
            ],
            "defaultStatus": "affected",
            "product": "Red Hat AI Inference Server 3.2",
            "vendor": "Red Hat"
          },
          {
            "cpes": [
              "cpe:/a:redhat:ai_inference_server:3.3::el9"
            ],
            "defaultStatus": "affected",
            "product": "Red Hat AI Inference Server 3.3",
            "vendor": "Red Hat"
          },
          {
            "cpes": [
              "cpe:/a:redhat:openshift_ai:2.25::el9"
            ],
            "defaultStatus": "affected",
            "product": "Red Hat OpenShift AI 2.25",
            "vendor": "Red Hat"
          },
          {
            "cpes": [
              "cpe:/a:redhat:openshift_ai:3.3::el9"
            ],
            "defaultStatus": "affected",
            "product": "Red Hat OpenShift AI 3.3",
            "vendor": "Red Hat"
          },
          {
            "cpes": [
              "cpe:/a:redhat:openshift_ai:3.4::el9"
            ],
            "defaultStatus": "affected",
            "product": "Red Hat OpenShift AI 3.4",
            "vendor": "Red Hat"
          },
          {
            "cpes": [
              "cpe:/a:redhat:ai_inference_server:3"
            ],
            "defaultStatus": "affected",
            "product": "Red Hat AI Inference Server",
            "vendor": "Red Hat"
          },
          {
            "cpes": [
              "cpe:/a:redhat:enterprise_linux_ai:3"
            ],
            "defaultStatus": "affected",
            "product": "Red Hat Enterprise Linux AI (RHEL AI) 3",
            "vendor": "Red Hat"
          },
          {
            "cpes": [
              "cpe:/a:redhat:openshift_ai"
            ],
            "defaultStatus": "affected",
            "product": "Red Hat OpenShift AI (RHOAI)",
            "vendor": "Red Hat"
          }
        ],
        "datePublic": "2026-01-21T21:13:11.894Z",
        "descriptions": [
          {
            "lang": "en",
            "value": "A flaw was found in vLLM, an inference and serving engine for large language models (LLMs). This vulnerability allows a remote attacker to achieve arbitrary code execution on the vLLM host during model loading. This occurs because vLLM loads Hugging Face `auto_map` dynamic modules without properly validating the `trust_remote_code` setting. By influencing the model repository or path, an attacker can execute malicious Python code at server startup, even before any API requests are handled."
          }
        ],
        "metrics": [
          {
            "other": {
              "content": {
                "namespace": "https://access.redhat.com/security/updates/classification/",
                "value": "Important"
              },
              "type": "Red Hat severity rating"
            }
          },
          {
            "cvssV3_1": {
              "attackComplexity": "LOW",
              "attackVector": "NETWORK",
              "availabilityImpact": "HIGH",
              "baseScore": 8.8,
              "baseSeverity": "HIGH",
              "confidentialityImpact": "HIGH",
              "integrityImpact": "HIGH",
              "privilegesRequired": "NONE",
              "scope": "UNCHANGED",
              "userInteraction": "REQUIRED",
              "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
              "version": "3.1"
            },
            "format": "CVSS"
          }
        ],
        "problemTypes": [
          {
            "descriptions": [
              {
                "cweId": "CWE-94",
                "description": "Improper Control of Generation of Code (\u0027Code Injection\u0027)",
                "lang": "en",
                "type": "CWE"
              }
            ]
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-06-30T12:06:46.679Z",
          "orgId": "0b0ca135-0b70-47e7-9f44-1890c2a1c46c",
          "shortName": "redhat-SADP"
        },
        "references": [
          {
            "tags": [
              "vdb-entry",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/security/cve/CVE-2026-22807"
          },
          {
            "name": "RHBZ#2431865",
            "tags": [
              "issue-tracking",
              "x_refsource_REDHAT"
            ],
            "url": "https://bugzilla.redhat.com/show_bug.cgi?id=2431865"
          },
          {
            "tags": [
              "x_sadp-csaf-vex"
            ],
            "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-22807.json"
          },
          {
            "tags": [
              "vendor-advisory",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/errata/RHSA-2026:3461"
          },
          {
            "tags": [
              "vendor-advisory",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/errata/RHSA-2026:3462"
          },
          {
            "tags": [
              "vendor-advisory",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/errata/RHSA-2026:30089"
          },
          {
            "tags": [
              "vendor-advisory",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/errata/RHSA-2026:30088"
          },
          {
            "tags": [
              "vendor-advisory",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/errata/RHSA-2026:30087"
          },
          {
            "tags": [
              "vendor-advisory",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/errata/RHSA-2026:10184"
          },
          {
            "tags": [
              "vendor-advisory",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/errata/RHSA-2026:3782"
          },
          {
            "tags": [
              "vendor-advisory",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/errata/RHSA-2026:3713"
          },
          {
            "tags": [
              "vendor-advisory",
              "x_refsource_REDHAT"
            ],
            "url": "https://access.redhat.com/errata/RHSA-2026:5119"
          }
        ],
        "solutions": [
          {
            "lang": "en",
            "value": "RHSA-2026:3461: Red Hat AI Inference Server 3.2"
          },
          {
            "lang": "en",
            "value": "RHSA-2026:3462: Red Hat AI Inference Server 3.2"
          },
          {
            "lang": "en",
            "value": "RHSA-2026:30089: Red Hat AI Inference Server 3.3"
          },
          {
            "lang": "en",
            "value": "RHSA-2026:30088: Red Hat AI Inference Server 3.3"
          },
          {
            "lang": "en",
            "value": "RHSA-2026:30087: Red Hat AI Inference Server 3.3"
          },
          {
            "lang": "en",
            "value": "RHSA-2026:10184: Red Hat OpenShift AI 2.25"
          },
          {
            "lang": "en",
            "value": "RHSA-2026:3782: Red Hat OpenShift AI 2.25"
          },
          {
            "lang": "en",
            "value": "RHSA-2026:3713: Red Hat OpenShift AI 3.3"
          },
          {
            "lang": "en",
            "value": "RHSA-2026:5119: Red Hat OpenShift AI 3.4"
          }
        ],
        "timeline": [
          {
            "lang": "en",
            "time": "2026-01-21T22:00:55.823Z",
            "value": "Reported to Red Hat."
          },
          {
            "lang": "en",
            "time": "2026-01-21T21:13:11.894Z",
            "value": "Made public."
          }
        ],
        "title": "vLLM: vLLM: Arbitrary code execution via untrusted model loading",
        "workarounds": [
          {
            "lang": "en",
            "value": "To mitigate this issue, ensure that vLLM instances are configured to load models only from trusted and verified repositories. Restrict access to the model repository path to prevent unauthorized modification or introduction of malicious code. Implement strict access controls and integrity checks for all model sources."
          }
        ],
        "x_adpType": "supplier",
        "x_generator": {
          "engine": "sadp-cli 1.0.0"
        }
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.10.1, \u003c 0.14.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 8.8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-94",
              "description": "CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-01-21T21:13:11.894Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/32194",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/32194"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5"
        },
        {
          "name": "https://github.com/vllm-project/vllm/releases/tag/v0.14.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/releases/tag/v0.14.0"
        }
      ],
      "source": {
        "advisory": "GHSA-2pc9-4j83-qjmr",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM affected by RCE via auto_map dynamic module loading during model initialization"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-22807",
    "datePublished": "2026-01-21T21:13:11.894Z",
    "dateReserved": "2026-01-09T22:50:10.288Z",
    "dateUpdated": "2026-06-30T12:06:46.679Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-22807",
      "date": "2026-07-05",
      "epss": "0.00737",
      "percentile": "0.50034"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-22807\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-01-21T22:15:49.077\",\"lastModified\":\"2026-06-30T03:17:28.227\",\"vulnStatus\":\"Modified\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.\"},{\"lang\":\"es\",\"value\":\"vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLM). A partir de la versi\u00f3n 0.10.1 y antes de la versi\u00f3n 0.14.0, vLLM carga m\u00f3dulos din\u00e1micos \u0027auto_map\u0027 de Hugging Face durante la resoluci\u00f3n del modelo sin depender de \u0027trust_remote_code\u0027, permitiendo que c\u00f3digo Python controlado por el atacante en un repositorio/ruta de modelo se ejecute al inicio del servidor. Un atacante que pueda influir en el repositorio/ruta del modelo (directorio local o repositorio remoto de Hugging Face) puede lograr la ejecuci\u00f3n de c\u00f3digo arbitrario en el host de vLLM durante la carga del modelo. Esto ocurre antes de cualquier manejo de solicitudes y no requiere acceso a la API. La versi\u00f3n 0.14.0 corrige el problema.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"vllm-project\",\"product\":\"vllm\",\"versions\":[{\"version\":\"\u003e= 0.10.1, \u003c 0.14.0\",\"status\":\"affected\"}]}]},{\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\",\"affectedData\":[{\"vendor\":\"Red Hat\",\"product\":\"Red Hat AI Inference Server 3.2\",\"defaultStatus\":\"affected\",\"cpes\":[\"cpe:/a:redhat:ai_inference_server:3.2::el9\"]},{\"vendor\":\"Red Hat\",\"product\":\"Red Hat AI Inference Server 3.3\",\"defaultStatus\":\"affected\",\"cpes\":[\"cpe:/a:redhat:ai_inference_server:3.3::el9\"]},{\"vendor\":\"Red Hat\",\"product\":\"Red Hat OpenShift AI 2.25\",\"defaultStatus\":\"affected\",\"cpes\":[\"cpe:/a:redhat:openshift_ai:2.25::el9\"]},{\"vendor\":\"Red Hat\",\"product\":\"Red Hat OpenShift AI 3.3\",\"defaultStatus\":\"affected\",\"cpes\":[\"cpe:/a:redhat:openshift_ai:3.3::el9\"]},{\"vendor\":\"Red Hat\",\"product\":\"Red Hat OpenShift AI 3.4\",\"defaultStatus\":\"affected\",\"cpes\":[\"cpe:/a:redhat:openshift_ai:3.4::el9\"]},{\"vendor\":\"Red Hat\",\"product\":\"Red Hat AI Inference Server\",\"defaultStatus\":\"affected\",\"cpes\":[\"cpe:/a:redhat:ai_inference_server:3\"]},{\"vendor\":\"Red Hat\",\"product\":\"Red Hat Enterprise Linux AI (RHEL AI) 3\",\"defaultStatus\":\"affected\",\"cpes\":[\"cpe:/a:redhat:enterprise_linux_ai:3\"]},{\"vendor\":\"Red Hat\",\"product\":\"Red Hat OpenShift AI (RHOAI)\",\"defaultStatus\":\"affected\",\"cpes\":[\"cpe:/a:redhat:openshift_ai\"]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\",\"baseScore\":8.8,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":2.8,\"impactScore\":5.9},{\"source\":\"nvd@nist.gov\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":9.8,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":3.9,\"impactScore\":5.9},{\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\",\"baseScore\":8.8,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":2.8,\"impactScore\":5.9}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-01-22T15:11:00.640100Z\",\"id\":\"CVE-2026-22807\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"total\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-94\"}]},{\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-94\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*\",\"versionStartIncluding\":\"0.10.1\",\"versionEndExcluding\":\"0.14.0\",\"matchCriteriaId\":\"F2E87BA6-DDF8-4FF6-A286-B44780082C69\"}]}]}],\"references\":[{\"url\":\"https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\"]},{\"url\":\"https://github.com/vllm-project/vllm/pull/32194\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Issue Tracking\",\"Patch\"]},{\"url\":\"https://github.com/vllm-project/vllm/releases/tag/v0.14.0\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Product\",\"Release Notes\"]},{\"url\":\"https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\",\"Vendor Advisory\"]},{\"url\":\"https://access.redhat.com/errata/RHSA-2026:10184\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://access.redhat.com/errata/RHSA-2026:30087\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://access.redhat.com/errata/RHSA-2026:30088\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://access.redhat.com/errata/RHSA-2026:30089\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://access.redhat.com/errata/RHSA-2026:3461\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://access.redhat.com/errata/RHSA-2026:3462\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://access.redhat.com/errata/RHSA-2026:3713\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://access.redhat.com/errata/RHSA-2026:3782\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://access.redhat.com/errata/RHSA-2026:5119\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://access.redhat.com/security/cve/CVE-2026-22807\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://bugzilla.redhat.com/show_bug.cgi?id=2431865\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"},{\"url\":\"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-22807.json\",\"source\":\"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"vLLM: vLLM: Arbitrary code execution via untrusted model loading\", \"metrics\": [{\"other\": {\"type\": \"Red Hat severity rating\", \"content\": {\"value\": \"Important\", \"namespace\": \"https://access.redhat.com/security/updates/classification/\"}}}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 8.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"cpes\": [\"cpe:/a:redhat:ai_inference_server:3.2::el9\"], \"vendor\": \"Red Hat\", \"product\": \"Red Hat AI Inference Server 3.2\", \"defaultStatus\": \"affected\"}, {\"cpes\": [\"cpe:/a:redhat:ai_inference_server:3.3::el9\"], \"vendor\": \"Red Hat\", \"product\": \"Red Hat AI Inference Server 3.3\", \"defaultStatus\": \"affected\"}, {\"cpes\": [\"cpe:/a:redhat:openshift_ai:2.25::el9\"], \"vendor\": \"Red Hat\", \"product\": \"Red Hat OpenShift AI 2.25\", \"defaultStatus\": \"affected\"}, {\"cpes\": [\"cpe:/a:redhat:openshift_ai:3.3::el9\"], \"vendor\": \"Red Hat\", \"product\": \"Red Hat OpenShift AI 3.3\", \"defaultStatus\": \"affected\"}, {\"cpes\": [\"cpe:/a:redhat:openshift_ai:3.4::el9\"], \"vendor\": \"Red Hat\", \"product\": \"Red Hat OpenShift AI 3.4\", \"defaultStatus\": \"affected\"}, {\"cpes\": [\"cpe:/a:redhat:ai_inference_server:3\"], \"vendor\": \"Red Hat\", \"product\": \"Red Hat AI Inference Server\", \"defaultStatus\": \"affected\"}, {\"cpes\": [\"cpe:/a:redhat:enterprise_linux_ai:3\"], \"vendor\": \"Red Hat\", \"product\": \"Red Hat Enterprise Linux AI (RHEL AI) 3\", \"defaultStatus\": \"affected\"}, {\"cpes\": [\"cpe:/a:redhat:openshift_ai\"], \"vendor\": \"Red Hat\", \"product\": \"Red Hat OpenShift AI (RHOAI)\", \"defaultStatus\": \"affected\"}], \"timeline\": [{\"lang\": \"en\", \"time\": \"2026-01-21T22:00:55.823Z\", \"value\": \"Reported to Red Hat.\"}, {\"lang\": \"en\", \"time\": \"2026-01-21T21:13:11.894Z\", \"value\": \"Made public.\"}], \"solutions\": [{\"lang\": \"en\", \"value\": \"RHSA-2026:3461: Red Hat AI Inference Server 3.2\"}, {\"lang\": \"en\", \"value\": \"RHSA-2026:3462: Red Hat AI Inference Server 3.2\"}, {\"lang\": \"en\", \"value\": \"RHSA-2026:30089: Red Hat AI Inference Server 3.3\"}, {\"lang\": \"en\", \"value\": \"RHSA-2026:30088: Red Hat AI Inference Server 3.3\"}, {\"lang\": \"en\", \"value\": \"RHSA-2026:30087: Red Hat AI Inference Server 3.3\"}, {\"lang\": \"en\", \"value\": \"RHSA-2026:10184: Red Hat OpenShift AI 2.25\"}, {\"lang\": \"en\", \"value\": \"RHSA-2026:3782: Red Hat OpenShift AI 2.25\"}, {\"lang\": \"en\", \"value\": \"RHSA-2026:3713: Red Hat OpenShift AI 3.3\"}, {\"lang\": \"en\", \"value\": \"RHSA-2026:5119: Red Hat OpenShift AI 3.4\"}], \"x_adpType\": \"supplier\", \"datePublic\": \"2026-01-21T21:13:11.894Z\", \"references\": [{\"url\": \"https://access.redhat.com/security/cve/CVE-2026-22807\", \"tags\": [\"vdb-entry\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://bugzilla.redhat.com/show_bug.cgi?id=2431865\", \"name\": \"RHBZ#2431865\", \"tags\": [\"issue-tracking\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-22807.json\", \"tags\": [\"x_sadp-csaf-vex\"]}, {\"url\": \"https://access.redhat.com/errata/RHSA-2026:3461\", \"tags\": [\"vendor-advisory\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://access.redhat.com/errata/RHSA-2026:3462\", \"tags\": [\"vendor-advisory\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://access.redhat.com/errata/RHSA-2026:30089\", \"tags\": [\"vendor-advisory\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://access.redhat.com/errata/RHSA-2026:30088\", \"tags\": [\"vendor-advisory\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://access.redhat.com/errata/RHSA-2026:30087\", \"tags\": [\"vendor-advisory\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://access.redhat.com/errata/RHSA-2026:10184\", \"tags\": [\"vendor-advisory\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://access.redhat.com/errata/RHSA-2026:3782\", \"tags\": [\"vendor-advisory\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://access.redhat.com/errata/RHSA-2026:3713\", \"tags\": [\"vendor-advisory\", \"x_refsource_REDHAT\"]}, {\"url\": \"https://access.redhat.com/errata/RHSA-2026:5119\", \"tags\": [\"vendor-advisory\", \"x_refsource_REDHAT\"]}], \"workarounds\": [{\"lang\": \"en\", \"value\": \"To mitigate this issue, ensure that vLLM instances are configured to load models only from trusted and verified repositories. Restrict access to the model repository path to prevent unauthorized modification or introduction of malicious code. Implement strict access controls and integrity checks for all model sources.\"}], \"x_generator\": {\"engine\": \"sadp-cli 1.0.0\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"A flaw was found in vLLM, an inference and serving engine for large language models (LLMs). This vulnerability allows a remote attacker to achieve arbitrary code execution on the vLLM host during model loading. This occurs because vLLM loads Hugging Face `auto_map` dynamic modules without properly validating the `trust_remote_code` setting. By influencing the model repository or path, an attacker can execute malicious Python code at server startup, even before any API requests are handled.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-94\", \"description\": \"Improper Control of Generation of Code (\u0027Code Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"0b0ca135-0b70-47e7-9f44-1890c2a1c46c\", \"shortName\": \"redhat-SADP\", \"dateUpdated\": \"2026-06-30T02:45:46.013Z\"}}, {\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-22807\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-01-22T15:11:00.640100Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-01-22T15:11:02.864Z\"}}], \"cna\": {\"title\": \"vLLM affected by RCE via auto_map dynamic module loading during model initialization\", \"source\": {\"advisory\": \"GHSA-2pc9-4j83-qjmr\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 8.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"HIGH\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"vendor\": \"vllm-project\", \"product\": \"vllm\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003e= 0.10.1, \u003c 0.14.0\"}]}], \"references\": [{\"url\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr\", \"name\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/vllm-project/vllm/pull/32194\", \"name\": \"https://github.com/vllm-project/vllm/pull/32194\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5\", \"name\": \"https://github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb024e5\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/vllm-project/vllm/releases/tag/v0.14.0\", \"name\": \"https://github.com/vllm-project/vllm/releases/tag/v0.14.0\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-94\", \"description\": \"CWE-94: Improper Control of Generation of Code (\u0027Code Injection\u0027)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-01-21T21:13:11.894Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-22807\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-06-30T02:45:46.013Z\", \"dateReserved\": \"2026-01-09T22:50:10.288Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-01-21T21:13:11.894Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

Sightings

Author Source Type Date Other

Nomenclature

  • Seen: The vulnerability was mentioned, discussed, or observed by the user.
  • Confirmed: The vulnerability has been validated from an analyst's perspective.
  • Published Proof of Concept: A public proof of concept is available for this vulnerability.
  • Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
  • Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
  • Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
  • Not confirmed: The user expressed doubt about the validity of the vulnerability.
  • Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.


Detection rules are retrieved from Rulezet.