Skip to main content
VulnerabilityPublished Updated

CVE-2026-90553: vLLM · Code Injection

Affects vLLMSource CVE Database V5

0

Not known to be exploited · CVSS 8.5 High : upgrade to 0.28.0 soon.

Data as of 27 Oct 2026, 05:11 UTC

CVSS 4.0 base score
8.5High
How severe the flaw is on the 0–10 CVSS scale.
EPSS
0.3% chance of exploitation in 30 days – higher than 23% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch
Available – fixed in 0.28.0
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 12 Sep 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponised: no evidence on record.

    No public exploit code indexed in Metasploit or Exploit-DB

  4. Exploited in the wild: no evidence on record.

    Not in CISA KEV and no source reports exploitation

  5. Observed by OffSeq Mirage: no evidence on record.

    No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

What to do

Upgrade vLLM and vllm to 0.28.0.

Affected software

ProductAffectedFixed in
vllm-projectvLLMAffected
  • <0.28.0
Fixed in
  • 0.28.0
PyPIvllmpkg:pypi/vllmOther threatsAffected
  • <0.28.0
Fixed in
  • 0.28.0

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Upgrade to vLLM version 0.28.0 or later, where this vulnerability is fixed. Until then, avoid loading untrusted remote processor classes or models.

Description

vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.

References

Community reviews

Loading reviews…