Skip to main content
VulnerabilityPublished

CVE-2026-130685: vllm · Improper Input Validation

Affects vllmSource CVE Database V5

0
Compare

Not known to be exploited · CVSS 8.7 High : upgrade to 0.33.0 soon.

Data as of 18 Nov 2026, 12:20 UTC

CVSS 4.0 base score
8.7High
How severe the flaw is on the 0–10 CVSS scale.

Thin evidence

One scorer or none
CVSS scores by source
CNA (VulnCheck)CVSS 4.08.7
CNA (VulnCheck)CVSS 3.17.5
Patch
Available – fixed in 0.33.0
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

Exploitation evidence

  1. Disclosed: evidence found.

    CVE published 18 Nov 2026

  2. Detectable: no evidence on record.

    No public nuclei template indexed

  3. Weaponized: 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 17 Nov 2026.

What to do

Upgrade vllm to 0.33.0.

Affected software

ProductAffectedFixed in
vllm-projectvllmAffected
  • >=0.28.0 <0.33.0
Fixed in
  • 0.33.0
PyPIvllmpkg:pypi/vllmOther threatsAffected
  • >=0.28.0 <0.33.0
Fixed in
  • 0.33.0

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

AI-suggested

Upgrade vLLM to version 0.33.0 or later, where this vulnerability is fixed. No other mitigations or workarounds are indicated. Since this is a direct input validation flaw, patching is the recommended and effective remediation.

Description

vLLM versions from 0.28.0 up to but not including 0.33.0 have an improper input validation vulnerability. This flaw allows unauthenticated attackers to crash the shared EngineCore by submitting out-of-range prompt token IDs when the service is run with the --skip-tokenizer-init option. Specifically, attackers can send large positive token IDs to certain API endpoints, bypassing vocabulary checks and causing a fatal embedding index error that results in denial of service for all tenants. The issue is fixed in version 0.33.0.

References

Community reviews

Loading reviews…