Vulnerability-Lookup

CVE-2026-27893 (GCVE-0-2026-27893)

Vulnerability from cvelistv5 – Published: 2026-03-26 23:56 – Updated: 2026-03-27 13:52

Title

vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out

Summary

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user's explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches 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

CWE

CWE-693 - Protection Mechanism Failure

Assigner

GitHub_M

References

URL

Tags

	https://github.com/vllm-project/vllm/security/adv…	x_refsource_CONFIRM
	https://github.com/vllm-project/vllm/pull/36192	x_refsource_MISC
	https://github.com/vllm-project/vllm/commit/00bd0…	x_refsource_MISC

Impacted products

	Vendor	Product	Version
	vllm-project	vllm	Affected: >= 0.10.1, < 0.18.0

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-27893",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-03-27T13:26:41.908182Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-03-27T13:52:33.526Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "vllm",
          "vendor": "vllm-project",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 0.10.1, \u003c 0.18.0"
            }
          ]
        }
      ],
      "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 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user\u0027s explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches 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-693",
              "description": "CWE-693: Protection Mechanism Failure",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-03-26T23:56:53.579Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59"
        },
        {
          "name": "https://github.com/vllm-project/vllm/pull/36192",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/pull/36192"
        },
        {
          "name": "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72"
        }
      ],
      "source": {
        "advisory": "GHSA-7972-pg2x-xr59",
        "discovery": "UNKNOWN"
      },
      "title": "vLLM\u0027s hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-27893",
    "datePublished": "2026-03-26T23:56:53.579Z",
    "dateReserved": "2026-02-24T15:19:29.717Z",
    "dateUpdated": "2026-03-27T13:52:33.526Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-27893\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-03-27T00:16:22.333\",\"lastModified\":\"2026-03-30T18:56:21.730\",\"vulnStatus\":\"Analyzed\",\"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 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user\u0027s explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches 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 0.18.0, dos archivos de implementaci\u00f3n de modelos codifican de forma r\u00edgida \u0027trust_remote_code=True\u0027 al cargar subcomponentes, eludiendo la exclusi\u00f3n voluntaria de seguridad expl\u00edcita del usuario \u0027--trust-remote-code=False\u0027. Esto permite la ejecuci\u00f3n remota de c\u00f3digo a trav\u00e9s de repositorios de modelos maliciosos incluso cuando el usuario ha deshabilitado expl\u00edcitamente la confianza en el c\u00f3digo remoto. La versi\u00f3n 0.18.0 corrige el problema.\"}],\"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}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-693\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*\",\"versionStartIncluding\":\"0.10.1\",\"versionEndExcluding\":\"0.18.0\",\"matchCriteriaId\":\"2130385B-68E6-4854-AC42-0CBA1F30B487\"}]}]}],\"references\":[{\"url\":\"https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Patch\"]},{\"url\":\"https://github.com/vllm-project/vllm/pull/36192\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Issue Tracking\"]},{\"url\":\"https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Vendor Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-27893\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-03-27T13:26:41.908182Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-03-27T13:26:45.730Z\"}}], \"cna\": {\"title\": \"vLLM\u0027s hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out\", \"source\": {\"advisory\": \"GHSA-7972-pg2x-xr59\", \"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 0.18.0\"}]}], \"references\": [{\"url\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59\", \"name\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/vllm-project/vllm/pull/36192\", \"name\": \"https://github.com/vllm-project/vllm/pull/36192\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72\", \"name\": \"https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72\", \"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 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user\u0027s explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-693\", \"description\": \"CWE-693: Protection Mechanism Failure\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-03-26T23:56:53.579Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-27893\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-03-27T13:52:33.526Z\", \"dateReserved\": \"2026-02-24T15:19:29.717Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-03-26T23:56:53.579Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-27893

Vulnerability from fkie_nvd - Published: 2026-03-27 00:16 - Updated: 2026-03-30 18:56

Severity ?

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/00bd08edeee5dd4d4c13277c0114a464011acf72	Patch
security-advisories@github.com	https://github.com/vllm-project/vllm/pull/36192	Issue Tracking
security-advisories@github.com	https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59	Vendor Advisory

Impacted products

	Vendor	Product	Version
	vllm	vllm	*

JSON

To clipboard

{
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "2130385B-68E6-4854-AC42-0CBA1F30B487",
              "versionEndExcluding": "0.18.0",
              "versionStartIncluding": "0.10.1",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "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 0.18.0, two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user\u0027s explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches 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 0.18.0, dos archivos de implementaci\u00f3n de modelos codifican de forma r\u00edgida \u0027trust_remote_code=True\u0027 al cargar subcomponentes, eludiendo la exclusi\u00f3n voluntaria de seguridad expl\u00edcita del usuario \u0027--trust-remote-code=False\u0027. Esto permite la ejecuci\u00f3n remota de c\u00f3digo a trav\u00e9s de repositorios de modelos maliciosos incluso cuando el usuario ha deshabilitado expl\u00edcitamente la confianza en el c\u00f3digo remoto. La versi\u00f3n 0.18.0 corrige el problema."
    }
  ],
  "id": "CVE-2026-27893",
  "lastModified": "2026-03-30T18:56:21.730",
  "metrics": {
    "cvssMetricV31": [
      {
        "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": "security-advisories@github.com",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-03-27T00:16:22.333",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Patch"
      ],
      "url": "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Issue Tracking"
      ],
      "url": "https://github.com/vllm-project/vllm/pull/36192"
    },
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Vendor Advisory"
      ],
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-693"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Primary"
    }
  ]
}

GHSA-7972-PG2X-XR59

Vulnerability from github – Published: 2026-03-27 15:27 – Updated: 2026-03-27 15:27

Summary

vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out

Details

Summary

Two model implementation files hardcode trust_remote_code=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust.

### Details

Affected files (latest main branch):

vllm/model_executor/models/nemotron_vl.py:430 ```python vision_model = AutoModel.from_config(config.vision_config, trust_remote_code=True)


  2. vllm/model_executor/models/kimi_k25.py:177

```python
  cached_get_image_processor(self.ctx.model_config.model, trust_remote_code=True)

Both pass a hardcoded trust_remote_code=True to HuggingFace API calls, overriding the user's global --trust-remote-code=False setting.

Relation to prior CVEs: - CVE-2025-66448 fixed auto_map resolution in vllm/transformers_utils/config.py (config loading path) - CVE-2026-22807 fixed broader auto_map at startup - Both fixes are present in the current code. These hardcoded instances in model files survived both patches — different code paths.

Impact

Remote code execution. An attacker can craft a malicious model repository that executes arbitrary Python code when loaded by vLLM, even when the user has explicitly set --trust-remote-code=False. This undermines the security guarantee that trust_remote_code=False is intended to provide.

Remediation: Replace hardcoded trust_remote_code=True with self.config.model_config.trust_remote_code in both files. Raise a clear error if the model component requires remote code but the user hasn't opted in.

Severity ?

8.8 (High)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/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": "0.10.1"
            },
            {
              "fixed": "0.18.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-27893"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-693"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-03-27T15:27:20Z",
    "nvd_published_at": "2026-03-27T00:16:22Z",
    "severity": "HIGH"
  },
  "details": "### Summary\n\n  Two model implementation files hardcode `trust_remote_code=True` when loading sub-components, bypassing the user\u0027s explicit `--trust-remote-code=False` security opt-out. This enables remote code execution via malicious model\n  repositories even when the user has explicitly disabled remote code trust.\n\n  ### Details\n\n  **Affected files (latest main branch):**\n\n  1. `vllm/model_executor/models/nemotron_vl.py:430`\n  ```python\n  vision_model = AutoModel.from_config(config.vision_config, trust_remote_code=True)\n```\n\n  2. vllm/model_executor/models/kimi_k25.py:177\n \n```python\n  cached_get_image_processor(self.ctx.model_config.model, trust_remote_code=True)\n```\n\n  Both pass a hardcoded trust_remote_code=True to HuggingFace API calls, overriding the user\u0027s global --trust-remote-code=False setting.\n\n  Relation to prior CVEs:\n  - CVE-2025-66448 fixed auto_map resolution in vllm/transformers_utils/config.py (config loading path)\n  - CVE-2026-22807 fixed broader auto_map at startup\n  - Both fixes are present in the current code. These hardcoded instances in model files survived both patches \u2014 different code paths.\n\n### Impact\n\n  Remote code execution. An attacker can craft a malicious model repository that executes arbitrary Python code when loaded by vLLM, even when the user has explicitly set --trust-remote-code=False. This undermines the security guarantee\n  that trust_remote_code=False is intended to provide.\n\n  Remediation: Replace hardcoded trust_remote_code=True with self.config.model_config.trust_remote_code in both files. Raise a clear error if the model component requires remote code but the user hasn\u0027t opted in.",
  "id": "GHSA-7972-pg2x-xr59",
  "modified": "2026-03-27T15:27:20Z",
  "published": "2026-03-27T15:27:20Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-27893"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/pull/36192"
    },
    {
      "type": "WEB",
      "url": "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/vllm-project/vllm"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "vLLM has Hardcoded Trust Override in Model Files Enables RCE Despite Explicit User Opt-Out"
}

Sightings

Author	Source	Type	Date

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.

Action not permitted

CVE-2026-27893 (GCVE-0-2026-27893)

FKIE_CVE-2026-27893

GHSA-7972-PG2X-XR59

Summary

Impact

Tags

Sightings

Nomenclature