CVE-2026-27893

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.

CVSS v3 8.8 HIGH

8.8^/10

CVSS v3 : HIGH

Vector :

Exploitability : 2.8 / Impact : 5.9

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope UNCHANGED

References

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

Configurations

Configuration 1 (hide)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

History

30 Mar 2026, 18:56

Type	Values Removed	Values Added
CPE		cpe:2.3:a:vllm:vllm::::::::
First Time		Vllm Vllm vllm
References	~~() https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72 -~~	() https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72 - Patch
References	~~() https://github.com/vllm-project/vllm/pull/36192 -~~	() https://github.com/vllm-project/vllm/pull/36192 - Issue Tracking
References	~~() https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59 -~~	() https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59 - Vendor Advisory

Information

Published : 2026-03-27 00:16

Updated : 2026-03-30 18:56

NVD link : CVE-2026-27893

Mitre link : CVE-2026-27893

CVE.ORG link : CVE-2026-27893

JSON object : View

Products Affected

vllm

vllm

CWE

CWE-693

Protection Mechanism Failure

{"id": "CVE-2026-27893", "cveTags": [], "metrics": {"cvssMetricV31": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"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"}, "impactScore": 5.9, "exploitabilityScore": 2.8}]}, "published": "2026-03-27T00:16:22.333", "references": [{"url": "https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72", "tags": ["Patch"], "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/pull/36192", "tags": ["Issue Tracking"], "source": "security-advisories@github.com"}, {"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59", "tags": ["Vendor Advisory"], "source": "security-advisories@github.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Primary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-693"}]}], "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'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."}, {"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 'trust_remote_code=True' al cargar subcomponentes, eludiendo la exclusi\u00f3n voluntaria de seguridad expl\u00edcita del usuario '--trust-remote-code=False'. 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."}], "lastModified": "2026-03-30T18:56:21.730", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "2130385B-68E6-4854-AC42-0CBA1F30B487", "versionEndExcluding": "0.18.0", "versionStartIncluding": "0.10.1"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}