Skip to content
fr Sign in
8.8 High

CVE-2026-27893 vLLM is an inference and serving engine for large language models (LLMs)

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.

Affected products and versions

Product Affected versions Fixed in
vllm 0.10 0.10.1 → < 0.18.0 0.18.0
Red Hat AI Inference Server 3.2 1779223651 earliest → < 1779223651 1779223651
Red Hat AI Inference Server 3.3 1775749857 earliest → < 1775749857 1775749857
Red Hat Enterprise Linux AI 3.3 1776938871 earliest → < 1776938871 1776938871
Red Hat OpenShift AI 2.25 1783998857 earliest → < 1783998857 1783998857
Red Hat OpenShift AI 3.3 1782996080 earliest → < 1782996080 1782996080
Red Hat AI Inference Server Versions not published
Red Hat OpenShift AI (RHOAI) Versions not published

References

Timeline

  1. Published
  2. Last modified

Other CVEs of vllm

The 121 CVEs of vllm →
CVE-2026-115918 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115917 vLLM is an inference and serving engine for large language models 3.4 Low CVE-2026-115916 vLLM is an inference and serving engine for large language models 6.5 Medium CVE-2026-115915 vLLM is an inference and serving engine for large language models 8.1 High
Track this CVE