CVE-2026-27893
vLLM's hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out
Description
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.
INFO
Published Date :
March 27, 2026, 12:16 a.m.
Last Modified :
July 10, 2026, 12:16 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | HIGH | [email protected] | ||||
| CVSS 3.1 | HIGH | 0b0ca135-0b70-47e7-9f44-1890c2a1c46c |
Solution
- Update vLLM to version 0.18.0 or later.
- Ensure `trust_remote_code` is configured securely.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-27893.
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-27893 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-27893
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-27893 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-27893 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Modified by 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Jul. 10, 2026
Action Type Old Value New Value Added Reference https://access.redhat.com/errata/RHSA-2026:37275 -
CVE Modified by 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Jul. 08, 2026
Action Type Old Value New Value Changed 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:enterprise_linux_ai:3.3::el9'], 'vendor': 'Red Hat', 'product': 'Red Hat Enterprise Linux AI 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:ai_inference_server:3'], 'vendor': 'Red Hat', 'product': 'Red Hat AI Inference Server', 'defaultStatus': 'affected'}, {'cpes': ['cpe:/a:redhat:openshift_ai'], 'vendor': 'Red Hat', 'product': 'Red Hat OpenShift AI (RHOAI)', 'defaultStatus': '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:enterprise_linux_ai:3.3::el9'], 'vendor': 'Red Hat', 'product': 'Red Hat Enterprise Linux AI 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:ai_inference_server:3'], 'vendor': 'Red Hat', 'product': 'Red Hat AI Inference Server', 'defaultStatus': 'affected'}, {'cpes': ['cpe:/a:redhat:openshift_ai'], 'vendor': 'Red Hat', 'product': 'Red Hat OpenShift AI (RHOAI)', 'defaultStatus': 'unaffected'}] -
CVE Modified by 0b0ca135-0b70-47e7-9f44-1890c2a1c46c
Jun. 30, 2026
Action Type Old Value New Value Added 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:enterprise_linux_ai:3.3::el9'], 'vendor': 'Red Hat', 'product': 'Red Hat Enterprise Linux AI 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:ai_inference_server:3'], 'vendor': 'Red Hat', 'product': 'Red Hat AI Inference Server', 'defaultStatus': 'affected'}, {'cpes': ['cpe:/a:redhat:openshift_ai'], 'vendor': 'Red Hat', 'product': 'Red Hat OpenShift AI (RHOAI)', 'defaultStatus': 'affected'}] Added CVSS V3.1 AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Added CWE CWE-501 Added Reference https://access.redhat.com/errata/RHSA-2026:10140 Added Reference https://access.redhat.com/errata/RHSA-2026:10141 Added Reference https://access.redhat.com/errata/RHSA-2026:19712 Added Reference https://access.redhat.com/errata/RHSA-2026:19724 Added Reference https://access.redhat.com/errata/RHSA-2026:19725 Added Reference https://access.redhat.com/errata/RHSA-2026:24977 Added Reference https://access.redhat.com/errata/RHSA-2026:8746 Added Reference https://access.redhat.com/errata/RHSA-2026:8747 Added Reference https://access.redhat.com/errata/RHSA-2026:8748 Added Reference https://access.redhat.com/security/cve/CVE-2026-27893 Added Reference https://bugzilla.redhat.com/show_bug.cgi?id=2452055 Added Reference https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-27893.json -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 17, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-27893', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'none'}, {'automatable': 'no'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-03-27T13:26:41.908182Z'} -
CVE Modified by [email protected]
Jun. 17, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'vllm-project', 'product': 'vllm', 'versions': [{'status': 'affected', 'version': '>= 0.10.1, < 0.18.0'}]}] -
Initial Analysis by [email protected]
Mar. 30, 2026
Action Type Old Value New Value Added CPE Configuration OR *cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* versions from (including) 0.10.1 up to (excluding) 0.18.0 Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72 Types: Patch Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/pull/36192 Types: Issue Tracking Added Reference Type GitHub, Inc.: https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59 Types: Vendor Advisory -
New CVE Received by [email protected]
Mar. 27, 2026
Action Type Old Value New Value Added Description 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. Added CVSS V3.1 AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H Added CWE CWE-693 Added Reference https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72 Added Reference https://github.com/vllm-project/vllm/pull/36192 Added Reference https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59