CyberSecBulletin
CVE-2026-27893NVD status: Modified

vllm: Protection Mechanism Failure

Published Updated By the CyberSecBulletin desk

CVE-2026-27893 is a high-severity protection mechanism failure vulnerability in vllm from Vllm-project, with a CVSS 3.1 base score of 8.8 out of 10. It can be exploited remotely over the network by an unauthenticated attacker, but only if a user takes part, for example by opening a link or file. Affected vllm versions: >= 0.10.1, < 0.18.0. The record does not name a fixed version, so check the vendor advisory. There is no confirmed exploitation so far. EPSS estimates a 1.4% chance of exploitation within 30 days, higher than 73% of scored CVEs.

Next patch cycle

High severity with no evidence of exploitation so far.

What to do

  1. Check which version of vllm you run against the affected versions below, and install the vendor's latest release.
  2. Read the advisory on github.com for workarounds and exact fixed builds.
  3. Until you can update, restrict network access to the affected service so it is not reachable from untrusted networks.
  4. Because the attack needs a user to take part, warn users about unexpected links and files related to this product until it is patched.

Affected products and versions

VendorProductAffected versionsFixed in
Vllm-projectvllm>= 0.10.1, < 0.18.0Not stated
Red HatRed Hat AI Inference Server 3.2Not specified in the recordNot stated
Red HatRed Hat AI Inference Server 3.3Not specified in the recordNot stated
Red HatRed Hat Enterprise Linux AI 3.3Not specified in the recordNot stated
Red HatRed Hat OpenShift AI 2.25Not specified in the recordNot stated
Red HatRed Hat OpenShift AI 3.3Not specified in the recordNot stated
Red HatRed Hat AI Inference ServerNot specified in the recordNot stated
Red HatRed Hat OpenShift AI (RHOAI)Not specified in the recordNot stated

Version data comes from the organisation that assigned the CVE. Confirm against the vendor advisory before deciding you are unaffected.

How the severity score breaks down

Attack vector
NetworkCan be exploited remotely over a network, including the internet.
Attack complexity
LowNo special conditions are needed; the attack works reliably.
Privileges required
NoneNo account or login is needed.
User interaction
RequiredA user must take an action such as opening a file or link.
Scope
UnchangedImpact stays within the vulnerable component.
Confidentiality
HighAll data handled by the component can be read.
Integrity
HighData or code can be modified at will.
Availability
HighThe component can be taken down completely.

Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H. Scored by CNA (github.com).

Scoring systemScoreSeverityScored by
CVSS 3.18.8HighCNA (github.com)
CVSS 3.18.8HighCNA

Official 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.

Source: the CVE record as published by its numbering authority, via NVD and CVE.org.

The underlying weakness: Protection Mechanism Failure

The product does not use or incorrectly uses a protection mechanism that provides sufficient defense against directed attacks against the product.

More Protection Mechanism Failure vulnerabilities (CWE-693)

Timeline

  1. CVE record published.
  2. CISA published its SSVC assessment (exploitation: none, automatable: no, technical impact: total).
  3. Record last changed materially (score, affected products, status or references).

References

Other vulnerabilities in vllm

All vllm vulnerabilities

Recent Protection Mechanism Failure vulnerabilities

Spotted an error? Tell us.