Skip to main content
VulnerabilityPublished

CVE-2026-93592: vllm · Improper Validation of Array Index

Affects vllmSource CVE Database V5

0
Compare

Not known to be exploited · CVSS 8.7 High : upgrade to 0.28.0 soon.

Data as of 2 Nov 2026, 22:58 UTC

CVSS 4.0 base score
8.7High
How severe the flaw is on the 0–10 CVSS scale.
EPSS
0.5% chance of exploitation in 30 days – higher than 45% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch
Available – fixed in 0.28.0
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 Sep 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 2 Nov 2026.

What to do

Upgrade vllm and vllm-project/vllm to 0.28.0.

Affected software

ProductAffectedFixed in
vllm-projectvllmAffected
  • <0.28.0
Fixed in
  • 0.28.0
GitHubvllm-project/vllmpkg:github/vllm-project/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 issue is fixed. Since the vulnerability affects versions before 0.28.0, applying the official fix by updating the software is recommended. No vendor advisory or patch link was provided, so confirm the patch availability from the vendor's official channels before deployment.

Description

vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that poisons the GPU context, causing all subsequent requests to fail until the process restarts.

References

Community reviews

Loading reviews…