vLLM affected by RCE via auto_map dynamic module loading during model initialization

Summary

CVECVE-2026-22807
StatePUBLISHED
AssignerGitHub_M
Source PriorityCVE Program / NVD first with legacy fallback
Published2026-01-21 22:15:49 UTC
Updated2026-06-30 03:17:28 UTC
DescriptionvLLM 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.

Risk And Classification

Primary CVSS: v3.1 9.8 CRITICAL from [email protected]

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

EPSS: 0.007370000 probability, percentile 0.499530000 (date 2026-07-01)

Problem Types: CWE-94 | CWE-94 CWE-94: Improper Control of Generation of Code ('Code Injection') | CWE-94 Improper Control of Generation of Code ('Code Injection')


VersionSourceTypeScoreSeverityVector
3.1[email protected]Primary9.8CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
3.1ADPCVSS8.8HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
3.1[email protected]Secondary8.8HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
3.10b0ca135-0b70-47e7-9f44-1890c2a1c46cSecondary8.8HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
3.1CNADECLARED8.8HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

CVSS v3.1 Breakdown

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

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

NVD Known Affected Configurations (CPE 2.3)

TypeVendorProductVersionUpdateEditionLanguage
Application Vllm Vllm All All All All

Vendor Declared Affected Products

SourceVendorProductVersionPlatforms
CNA Vllm-project Vllm affected >= 0.10.1, < 0.14.0 Not specified
ADP Red Hat Red Hat AI Inference Server 3.2 Not specified Not specified
ADP Red Hat Red Hat AI Inference Server 3.3 Not specified Not specified
ADP Red Hat Red Hat OpenShift AI 2.25 Not specified Not specified
ADP Red Hat Red Hat OpenShift AI 3.3 Not specified Not specified
ADP Red Hat Red Hat OpenShift AI 3.4 Not specified Not specified
ADP Red Hat Red Hat AI Inference Server Not specified Not specified
ADP Red Hat Red Hat Enterprise Linux AI RHEL AI 3 Not specified Not specified
ADP Red Hat Red Hat OpenShift AI RHOAI Not specified Not specified

References

ReferenceSourceLinkTags
access.redhat.com/security/cve/CVE-2026-22807 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
access.redhat.com/errata/RHSA-2026:3462 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
github.com/vllm-project/vllm/pull/32194 [email protected] github.com Issue Tracking, Patch
access.redhat.com/errata/RHSA-2026:5119 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
access.redhat.com/errata/RHSA-2026:3782 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
access.redhat.com/errata/RHSA-2026:10184 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
github.com/vllm-project/vllm/commit/78d13ea9de4b1ce5e4d8a5af9738fea71fb0... [email protected] github.com Patch
github.com/vllm-project/vllm/releases/tag/v0.14.0 [email protected] github.com Product, Release Notes
access.redhat.com/errata/RHSA-2026:30089 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
access.redhat.com/errata/RHSA-2026:30087 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
access.redhat.com/errata/RHSA-2026:30088 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
access.redhat.com/errata/RHSA-2026:3713 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
github.com/vllm-project/vllm/security/advisories/GHSA-2pc9-4j83-qjmr [email protected] github.com Patch, Vendor Advisory
security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-22807.json 0b0ca135-0b70-47e7-9f44-1890c2a1c46c security.access.redhat.com
bugzilla.redhat.com/show_bug.cgi 0b0ca135-0b70-47e7-9f44-1890c2a1c46c bugzilla.redhat.com
access.redhat.com/errata/RHSA-2026:3461 0b0ca135-0b70-47e7-9f44-1890c2a1c46c access.redhat.com
CVE Program record CVE.ORG www.cve.org canonical
NVD vulnerability detail NVD nvd.nist.gov canonical, analysis

Additional Advisory Data

SourceTimeEvent
ADP2026-01-21T22:00:55.823ZReported to Red Hat.
ADP2026-01-21T21:13:11.894ZMade public.

Solutions

ADP: RHSA-2026:3461: Red Hat AI Inference Server 3.2

ADP: RHSA-2026:3462: Red Hat AI Inference Server 3.2

ADP: RHSA-2026:30089: Red Hat AI Inference Server 3.3

ADP: RHSA-2026:30088: Red Hat AI Inference Server 3.3

ADP: RHSA-2026:30087: Red Hat AI Inference Server 3.3

ADP: RHSA-2026:10184: Red Hat OpenShift AI 2.25

ADP: RHSA-2026:3782: Red Hat OpenShift AI 2.25

ADP: RHSA-2026:3713: Red Hat OpenShift AI 3.3

ADP: RHSA-2026:5119: Red Hat OpenShift AI 3.4

Workarounds

ADP: 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.

© CVE.report 2026 |

Use of this information constitutes acceptance for use in an AS IS condition. There are NO warranties, implied or otherwise, with regard to this information or its use. Any use of this information is at the user's risk. It is the responsibility of user to evaluate the accuracy, completeness or usefulness of any information, opinion, advice or other content. EACH USER WILL BE SOLELY RESPONSIBLE FOR ANY consequences of his or her direct or indirect use of this web site. ALL WARRANTIES OF ANY KIND ARE EXPRESSLY DISCLAIMED. This site will NOT BE LIABLE FOR ANY DIRECT, INDIRECT or any other kind of loss.

CVE, CWE, and OVAL are registred trademarks of The MITRE Corporation and the authoritative source of CVE content is MITRE's CVE web site. This site includes MITRE data granted under the following license.

Free CVE JSON API cve.report/api

CVE.report and Source URL Uptime Status status.cve.report