Vulnerability-Lookup

CVE-2025-66448 (GCVE-0-2025-66448)

Vulnerability from cvelistv5 – Published: 2025-12-01 22:45 – Updated: 2025-12-02 14:14

Title

vLLM vulnerable to remote code execution via transformers_utils/get_config

Summary

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host. This vulnerability is fixed in 0.11.1.

Severity

7.1 (High)


                        
                          CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H

SSVC

Exploitation: none Automatable: yes Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2025-12-02 14:14 UTC

CWE

CWE-94 - Improper Control of Generation of Code ('Code Injection')

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7639 records in the last 180 days details

References

3 references

URL	Tags
https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
https://github.com/vllm-project/vllm/pull/28126	x_refsource_MISC
https://github.com/vllm-project/vllm/commit/ffb08…	x_refsource_MISC

Impacted products

1 product

Vendor	Product	Version	CPE status
vllm-project	vllm	Affected: < 0.11.1	guessed

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2025-66448",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-12-02T14:14:49.921511Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2025-12-02T14:14:58.324Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.11.1"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend\u2019s code on the victim host. This vulnerability is fixed in 0.11.1."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 7.1,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/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": "2025-12-01T22:45:42.566Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/28126",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/28126"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"
        }
      ],
      "source": {
        "advisory": "GHSA-8fr4-5q9j-m8gm",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM vulnerable to remote code execution via transformers_utils/get_config"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2025-66448",
    "datePublished": "2025-12-01T22:45:42.566Z",
    "dateReserved": "2025-12-01T18:22:06.865Z",
    "dateUpdated": "2025-12-02T14:14:58.324Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2025-66448",
      "date": "2026-10-20",
      "epss": "0.0066",
      "percentile": "0.50695"
    },
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "vllm",
                "vendor": "vllm-project",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003c 0.11.1"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "configurations": [
          {
            "nodes": [
              {
                "cpeMatch": [
                  {
                    "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
                    "matchCriteriaId": "1501709D-1515-4B83-89CB-6F7FD4F81C4D",
                    "versionEndExcluding": "0.11.1",
                    "vulnerable": true
                  }
                ],
                "negate": false,
                "operator": "OR"
              }
            ]
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend\u2019s code on the victim host. This vulnerability is fixed in 0.11.1."
          },
          {
            "lang": "es",
            "value": "vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLM). Versiones anteriores a la 0.11.1, vLLM tiene un vector cr\u00edtico de ejecuci\u00f3n remota de c\u00f3digo en una clase de configuraci\u00f3n llamada Nemotron_Nano_VL_Config. Cuando vLLM carga una configuraci\u00f3n de modelo que contiene una entrada \u0027auto_map\u0027, la clase de configuraci\u00f3n resuelve ese mapeo con \u0027get_class_from_dynamic_module(...)\u0027 e instancia inmediatamente la clase devuelta. Esto obtiene y ejecuta c\u00f3digo Python del repositorio remoto referenciado en la cadena \u0027auto_map\u0027. Fundamentalmente, esto ocurre incluso cuando el llamador establece expl\u00edcitamente \u0027trust_remote_code=False\u0027 en \u0027vllm.transformers_utils.config.get_config\u0027. En la pr\u00e1ctica, un atacante puede publicar un repositorio frontend de apariencia inofensiva cuyo \u0027config.json\u0027 apunte, a trav\u00e9s de \u0027auto_map\u0027, a un repositorio backend malicioso separado; cargar el frontend ejecutar\u00e1 silenciosamente el c\u00f3digo del backend en el host de la v\u00edctima. Esta vulnerabilidad est\u00e1 corregida en la versi\u00f3n 0.11.1."
          }
        ],
        "id": "CVE-2025-66448",
        "lastModified": "2026-10-18T18:10:00.100",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 7.1,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H",
                "version": "3.1"
              },
              "exploitabilityScore": 1.2,
              "impactScore": 5.9,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            },
            {
              "cvssData": {
                "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"
              },
              "exploitabilityScore": 2.8,
              "impactScore": 5.9,
              "source": "nvd@nist.gov",
              "type": "Primary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2025-66448",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "yes"
                  },
                  {
                    "technicalImpact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2025-12-02T14:14:49.921511Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2025-12-01T23:15:54.213",
        "references": [
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Patch"
            ],
            "url": "https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Issue Tracking"
            ],
            "url": "https://github.com/vllm-project/vllm/pull/28126"
          },
          {
            "source": "security-advisories@github.com",
            "tags": [
              "Vendor Advisory"
            ],
            "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Analyzed",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-94"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "aggregate_severity": "Important",
      "current_release_date": "2026-09-21T16:28:50+00:00",
      "cve": "CVE-2025-66448",
      "id": "CVE-2025-66448",
      "initial_release_date": "2025-12-01T22:45:42.566000+00:00",
      "product_status:fixed": "37",
      "product_status:known_affected": "16",
      "product_status:known_not_affected": "653",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "vllm: vLLM: Remote Code Execution via malicious model configuration",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2025/cve-2025-66448.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2025-66448",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "yes"
                      },
                      {
                        "Technical Impact": "total"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2025-12-02T14:14:49.921511Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2025-12-02T14:14:54.375Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "vllm",
              "vendor": "vllm-project",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003c 0.11.1"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend\u2019s code on the victim host. This vulnerability is fixed in 0.11.1."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "HIGH",
                "attackVector": "NETWORK",
                "availabilityImpact": "HIGH",
                "baseScore": 7.1,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "HIGH",
                "integrityImpact": "HIGH",
                "privilegesRequired": "LOW",
                "scope": "UNCHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/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": "2025-12-01T22:45:42.566Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"
            },
            {
              "name": "https://github.com/vllm-project/vllm/pull/28126",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/pull/28126"
            },
            {
              "name": "https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"
            }
          ],
          "source": {
            "advisory": "GHSA-8fr4-5q9j-m8gm",
            "discovery": "UNKNOWN"
          },
          "title": "vLLM vulnerable to remote code execution via transformers_utils/get_config"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2025-66448",
        "datePublished": "2025-12-01T22:45:42.566Z",
        "dateReserved": "2025-12-01T18:22:06.865Z",
        "dateUpdated": "2025-12-02T14:14:58.324Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

CERTFR-2025-AVI-1138

Vulnerability from certfr_avis - Published: 2025-12-26 - Updated: 2025-12-26

De multiples vulnérabilités ont été découvertes dans VMware Tanzu Platform. Elles permettent à un attaquant de provoquer un problème de sécurité non spécifié par l'éditeur.

Solutions

Se référer au bulletin de sécurité de l'éditeur pour l'obtention des correctifs (cf. section Documentation).

Impacted products

	Vendor	Product	Description
	VMware	Tanzu Platform	AI Services pour Tanzu Platform versions antérieures à 10.3.2

References

Title

Publication Time

FKIE_CVE-2025-66448

Vulnerability from fkie_nvd - Published: 2025-12-01 23:15 - Updated: 2026-10-18 18:10

Severity

7.1 (High) - CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H
8.8 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Summary

References

URL	Tags
security-advisories@github.com	https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86	Patch
security-advisories@github.com	https://github.com/vllm-project/vllm/pull/28126	Issue Tracking
security-advisories@github.com	https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm	Vendor Advisory

Impacted products

	Vendor	Product	Version
	vllm	vllm	*

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.11.1"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "1501709D-1515-4B83-89CB-6F7FD4F81C4D",
              "versionEndExcluding": "0.11.1",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.11.1, vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend\u2019s code on the victim host. This vulnerability is fixed in 0.11.1."
    },
    {
      "lang": "es",
      "value": "vLLM es un motor de inferencia y servicio para modelos de lenguaje grandes (LLM). Versiones anteriores a la 0.11.1, vLLM tiene un vector cr\u00edtico de ejecuci\u00f3n remota de c\u00f3digo en una clase de configuraci\u00f3n llamada Nemotron_Nano_VL_Config. Cuando vLLM carga una configuraci\u00f3n de modelo que contiene una entrada \u0027auto_map\u0027, la clase de configuraci\u00f3n resuelve ese mapeo con \u0027get_class_from_dynamic_module(...)\u0027 e instancia inmediatamente la clase devuelta. Esto obtiene y ejecuta c\u00f3digo Python del repositorio remoto referenciado en la cadena \u0027auto_map\u0027. Fundamentalmente, esto ocurre incluso cuando el llamador establece expl\u00edcitamente \u0027trust_remote_code=False\u0027 en \u0027vllm.transformers_utils.config.get_config\u0027. En la pr\u00e1ctica, un atacante puede publicar un repositorio frontend de apariencia inofensiva cuyo \u0027config.json\u0027 apunte, a trav\u00e9s de \u0027auto_map\u0027, a un repositorio backend malicioso separado; cargar el frontend ejecutar\u00e1 silenciosamente el c\u00f3digo del backend en el host de la v\u00edctima. Esta vulnerabilidad est\u00e1 corregida en la versi\u00f3n 0.11.1."
    }
  ],
  "id": "CVE-2025-66448",
  "lastModified": "2026-10-18T18:10:00.100",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "HIGH",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 7.1,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "REQUIRED",
          "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 1.2,
        "impactScore": 5.9,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      },
      {
        "cvssData": {
          "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"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 5.9,
        "source": "nvd@nist.gov",
        "type": "Primary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2025-66448",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "yes"
            },
            {
              "technicalImpact": "total"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2025-12-02T14:14:49.921511Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2025-12-01T23:15:54.213",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Issue Tracking"
      ],
      "url": "https://github.com/vllm-project/vllm/pull/28126"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Vendor Advisory"
      ],
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-94"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-8FR4-5Q9J-M8GM

Vulnerability from github – Published: 2025-12-02 17:34 – Updated: 2026-07-17 16:16

Summary

vLLM vulnerable to remote code execution via transformers_utils/get_config

Details

Summary

vllm has a critical remote code execution vector in a config class named Nemotron_Nano_VL_Config. When vllm loads a model config that contains an auto_map entry, the config class resolves that mapping with get_class_from_dynamic_module(...) and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the auto_map string. Crucially, this happens even when the caller explicitly sets trust_remote_code=False in vllm.transformers_utils.config.get_config. In practice, an attacker can publish a benign-looking frontend repo whose config.json points via auto_map to a separate malicious backend repo; loading the frontend will silently run the backend’s code on the victim host.

Details

The vulnerable code resolves and instantiates classes from auto_map entries without checking whether those entries point to a different repo or whether remote code execution is allowed.

class Nemotron_Nano_VL_Config(PretrainedConfig):
    model_type = 'Llama_Nemotron_Nano_VL'

    def __init__(self, **kwargs):
        super().__init__(**kwargs)

        if vision_config is not None:
            assert "auto_map" in vision_config and "AutoConfig" in vision_config["auto_map"]
            # <-- vulnerable dynamic resolution + instantiation happens here
            vision_auto_config = get_class_from_dynamic_module(*vision_config["auto_map"]["AutoConfig"].split("--")[::-1])
            self.vision_config = vision_auto_config(**vision_config)
        else:
            self.vision_config = PretrainedConfig()

get_class_from_dynamic_module(...) is capable of fetching and importing code from the Hugging Face repo specified in the mapping. trust_remote_code is not enforced for this code path. As a result, a frontend repo can redirect the loader to any backend repo and cause code execution, bypassing the trust_remote_code guard.

Impact

This is a critical vulnerability because it breaks the documented trust_remote_code safety boundary in a core model-loading utility. The vulnerable code lives in a common loading path, so any application, service, CI job, or developer machine that uses vllm’s transformer utilities to load configs can be affected. The attack requires only two repos and no user interaction beyond loading the frontend model. A successful exploit can execute arbitrary commands on the host.

Fixes

https://github.com/vllm-project/vllm/pull/28126

Severity

7.1 (High)


                  
                    CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.11.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2025-66448"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-94"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2025-12-02T17:34:16Z",
    "nvd_published_at": "2025-12-01T23:15:54Z",
    "severity": "HIGH"
  },
  "details": "### Summary\n\n`vllm` has a critical remote code execution vector in a config class named `Nemotron_Nano_VL_Config`. When `vllm` loads a model config that contains an `auto_map` entry, the config class resolves that mapping with `get_class_from_dynamic_module(...)` and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the `auto_map` string. Crucially, this happens even when the caller explicitly sets `trust_remote_code=False` in `vllm.transformers_utils.config.get_config`. In practice, an attacker can publish a benign-looking frontend repo whose `config.json` points via `auto_map` to a separate malicious backend repo; loading the frontend will silently run the backend\u2019s code on the victim host.\n\n### Details\n\nThe vulnerable code resolves and instantiates classes from `auto_map` entries without checking whether those entries point to a different repo or whether remote code execution is allowed.\n\n```python\nclass Nemotron_Nano_VL_Config(PretrainedConfig):\n    model_type = \u0027Llama_Nemotron_Nano_VL\u0027\n\n    def __init__(self, **kwargs):\n        super().__init__(**kwargs)\n\n        if vision_config is not None:\n            assert \"auto_map\" in vision_config and \"AutoConfig\" in vision_config[\"auto_map\"]\n            # \u003c-- vulnerable dynamic resolution + instantiation happens here\n            vision_auto_config = get_class_from_dynamic_module(*vision_config[\"auto_map\"][\"AutoConfig\"].split(\"--\")[::-1])\n            self.vision_config = vision_auto_config(**vision_config)\n        else:\n            self.vision_config = PretrainedConfig()\n```\n\n`get_class_from_dynamic_module(...)` is capable of fetching and importing code from the Hugging Face repo specified in the mapping. `trust_remote_code` is not enforced for this code path. As a result, a frontend repo can redirect the loader to any backend repo and cause code execution, bypassing the `trust_remote_code` guard.\n\n### Impact\n\nThis is a critical vulnerability because it breaks the documented `trust_remote_code` safety boundary in a core model-loading utility. The vulnerable code lives in a common loading path, so any application, service, CI job, or developer machine that uses `vllm`\u2019s transformer utilities to load configs can be affected. The attack requires only two repos and no user interaction beyond loading the frontend model. A successful exploit can execute arbitrary commands on the host.\n\n### Fixes\n\n* https://github.com/vllm-project/vllm/pull/28126",
  "id": "GHSA-8fr4-5q9j-m8gm",
  "modified": "2026-07-17T16:16:28Z",
  "published": "2025-12-02T17:34:16Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-66448"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/28126"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-8fr4-5q9j-m8gm"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2015.yaml"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "WEB",
      "url": "https://pypi.org/project/vllm"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM vulnerable to remote code execution via transformers_utils/get_config"
}

PYSEC-2026-2015

Vulnerability from pysec - Published: 2026-07-07 16:03 - Updated: 2026-07-07 17:25

Details

Summary

Details

The vulnerable code resolves and instantiates classes from auto_map entries without checking whether those entries point to a different repo or whether remote code execution is allowed.

class Nemotron_Nano_VL_Config(PretrainedConfig):
    model_type = 'Llama_Nemotron_Nano_VL'

    def __init__(self, **kwargs):
        super().__init__(**kwargs)

        if vision_config is not None:
            assert "auto_map" in vision_config and "AutoConfig" in vision_config["auto_map"]
            # <-- vulnerable dynamic resolution + instantiation happens here
            vision_auto_config = get_class_from_dynamic_module(*vision_config["auto_map"]["AutoConfig"].split("--")[::-1])
            self.vision_config = vision_auto_config(**vision_config)
        else:
            self.vision_config = PretrainedConfig()

Impact

Fixes

https://github.com/vllm-project/vllm/pull/28126

Severity

7.1 (High)


                  
                    CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H

Impacted products

Name	purl
vllm	pkg:pypi/vllm

Aliases

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "vllm",
        "purl": "pkg:pypi/vllm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.11.1"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ],
      "versions": [
        "0.0.1",
        "0.1.0",
        "0.1.1",
        "0.1.2",
        "0.1.3",
        "0.1.4",
        "0.1.5",
        "0.1.6",
        "0.1.7",
        "0.10.0",
        "0.10.1",
        "0.10.1.1",
        "0.10.2",
        "0.11.0",
        "0.2.0",
        "0.2.1",
        "0.2.1.post1",
        "0.2.2",
        "0.2.3",
        "0.2.4",
        "0.2.5",
        "0.2.6",
        "0.2.7",
        "0.3.0",
        "0.3.1",
        "0.3.2",
        "0.3.3",
        "0.4.0",
        "0.4.0.post1",
        "0.4.1",
        "0.4.2",
        "0.4.3",
        "0.5.0",
        "0.5.0.post1",
        "0.5.1",
        "0.5.2",
        "0.5.3",
        "0.5.3.post1",
        "0.5.4",
        "0.5.5",
        "0.6.0",
        "0.6.1",
        "0.6.1.post1",
        "0.6.1.post2",
        "0.6.2",
        "0.6.3",
        "0.6.3.post1",
        "0.6.4",
        "0.6.4.post1",
        "0.6.5",
        "0.6.6",
        "0.6.6.post1",
        "0.7.0",
        "0.7.1",
        "0.7.2",
        "0.7.3",
        "0.8.0",
        "0.8.1",
        "0.8.2",
        "0.8.3",
        "0.8.4",
        "0.8.5",
        "0.8.5.post1",
        "0.9.0",
        "0.9.0.1",
        "0.9.1",
        "0.9.2"
      ]
    }
  ],
  "aliases": [
    "CVE-2025-66448",
    "GHSA-8fr4-5q9j-m8gm"
  ],
  "details": "### Summary\n\n`vllm` has a critical remote code execution vector in a config class named `Nemotron_Nano_VL_Config`. When `vllm` loads a model config that contains an `auto_map` entry, the config class resolves that mapping with `get_class_from_dynamic_module(...)` and immediately instantiates the returned class. This fetches and executes Python from the remote repository referenced in the `auto_map` string. Crucially, this happens even when the caller explicitly sets `trust_remote_code=False` in `vllm.transformers_utils.config.get_config`. In practice, an attacker can publish a benign-looking frontend repo whose `config.json` points via `auto_map` to a separate malicious backend repo; loading the frontend will silently run the backend\u2019s code on the victim host.\n\n### Details\n\nThe vulnerable code resolves and instantiates classes from `auto_map` entries without checking whether those entries point to a different repo or whether remote code execution is allowed.\n\n```python\nclass Nemotron_Nano_VL_Config(PretrainedConfig):\n    model_type = \u0027Llama_Nemotron_Nano_VL\u0027\n\n    def __init__(self, **kwargs):\n        super().__init__(**kwargs)\n\n        if vision_config is not None:\n            assert \"auto_map\" in vision_config and \"AutoConfig\" in vision_config[\"auto_map\"]\n            # \u003c-- vulnerable dynamic resolution + instantiation happens here\n            vision_auto_config = get_class_from_dynamic_module(*vision_config[\"auto_map\"][\"AutoConfig\"].split(\"--\")[::-1])\n            self.vision_config = vision_auto_config(**vision_config)\n        else:\n            self.vision_config = PretrainedConfig()\n```\n\n`get_class_from_dynamic_module(...)` is capable of fetching and importing code from the Hugging Face repo specified in the mapping. `trust_remote_code` is not enforced for this code path. As a result, a frontend repo can redirect the loader to any backend repo and cause code execution, bypassing the `trust_remote_code` guard.\n\n### Impact\n\nThis is a critical vulnerability because it breaks the documented `trust_remote_code` safety boundary in a core model-loading utility. The vulnerable code lives in a common loading path, so any application, service, CI job, or developer machine that uses `vllm`\u2019s transformer utilities to load configs can be affected. The attack requires only two repos and no user interaction beyond loading the frontend model. A successful exploit can execute arbitrary commands on the host.\n\n### Fixes\n\n* https://github.com/vllm-project/vllm/pull/28126",
  "id": "PYSEC-2026-2015",
  "modified": "2026-07-07T17:25:47.489502Z",
  "published": "2026-07-07T16:03:11.918128Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8fr4-5q9j-m8gm"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2025-66448"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/28126"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/ffb08379d8870a1a81ba82b72797f196838d0c86"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    },
    {
      "type": "PACKAGE",
      "url": "https://pypi.org/project/vllm"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-8fr4-5q9j-m8gm"
    }
  ],
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM vulnerable to remote code execution via transformers_utils/get_config"
}

RHSA-2025:23078

Vulnerability from csaf_redhat - Published: 2025-12-10 18:24 - Updated: 2026-10-21 04:49

Summary

Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (CUDA)

Severity

Important

Scope

20 vulnerabilities in this advisory, including CVE-2025-66448.

CVE-2025-66448

A remote code execution vulnerability has been identified in vLLM. An attacker can exploit a weakness in the model loading process to silently fetch and run unauthorized, malicious Python code on the host system. This happens because the engine mistakenly executes code from a remote repository referenced in a model's configuration, even when explicit security measures are set to prevent it.

7.5 (High)


                
                  CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

Fixed: 2 products

https://access.redhat.com/errata/RHSA-2025:23078

Open the full advisory

RHSA-2025:23079

Vulnerability from csaf_redhat - Published: 2025-12-10 18:25 - Updated: 2026-10-21 04:49

Summary

Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (ROCm)

Severity

Important

Scope

20 vulnerabilities in this advisory, including CVE-2025-66448.

CVE-2025-66448

7.5 (High)


                
                  CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

Fixed: 1 product

https://access.redhat.com/errata/RHSA-2025:23079

Open the full advisory

RHSA-2025:23080

Vulnerability from csaf_redhat - Published: 2025-12-10 18:26 - Updated: 2026-10-21 04:49

Summary

Red Hat Security Advisory: Red Hat AI Inference Server Model Optimization Tools 3.2.2 (CUDA)

Severity

Important

Scope

20 vulnerabilities in this advisory, including CVE-2025-66448.

CVE-2025-66448

7.5 (High)


                
                  CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

Fixed: 2 products

https://access.redhat.com/errata/RHSA-2025:23080

Open the full advisory

RHSA-2025:23204

Vulnerability from csaf_redhat - Published: 2025-12-15 15:38 - Updated: 2026-10-21 04:49

Summary

Red Hat Security Advisory: Red Hat AI Inference Server 3.2.5 (CUDA)

Severity

Important

Scope

11 vulnerabilities in this advisory, including CVE-2025-66448.

CVE-2025-66448

7.5 (High)


                
                  CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

Fixed: 2 products

https://access.redhat.com/errata/RHSA-2025:23204

Open the full advisory

RHSA-2025:23205

Vulnerability from csaf_redhat - Published: 2025-12-15 15:38 - Updated: 2026-10-21 04:49

Summary

Red Hat Security Advisory: Red Hat AI Inference Server 3.2.5 (ROCm)

Severity

Important

Scope

11 vulnerabilities in this advisory, including CVE-2025-66448.

CVE-2025-66448

7.5 (High)


                
                  CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

Fixed: 1 product

https://access.redhat.com/errata/RHSA-2025:23205

Open the full advisory

RHSA-2025:23209

Vulnerability from csaf_redhat - Published: 2025-12-15 15:50 - Updated: 2026-10-21 04:49

Summary

Red Hat Security Advisory: Red Hat AI Inference Server 3.2.5 (TPU)

Severity

Important

Scope

10 vulnerabilities in this advisory, including CVE-2025-66448.

CVE-2025-66448

7.5 (High)


                
                  CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:H/I:H/A:H

Fixed: 1 product

https://access.redhat.com/errata/RHSA-2025:23209

Open the full advisory

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.

Vulnerability timeline

Sightings and recorded dates, grouped by day · UTC

Order JSON

Publication & reservation Sightings KEV catalogs Other timestamps

Loading timeline…

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted

CVE-2025-66448 (GCVE-0-2025-66448)

Solutions

Summary

Details

Impact

Fixes

Summary

Details

Impact

Fixes

Tags

Sightings

Nomenclature

Vulnerability timeline

Related by attack behaviour