8.2

CVE-2026-100652: vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids

Analyzed
AliasesPYSEC-2026-4185GHSA-qff2-492f-9fm4
Published 26-09-2026Last modified 28-09-2026

Vulnerability summary

CVE-2026-100652 is a high (CVSS 8.2) Improper Input Validation vulnerability in vllm-project vllm. EPSS estimates a 0.36% chance of exploitation in the next 30 days, higher than 28.7% of scored vulnerabilities. 1 public exploit is recorded.

Overall risk
43/100
0100
Medium · default modelHow is this calculated?
CVSS score
8.2/10
010
High · v4.0 (CVE.org)
EPSS score
0.36%
0%100%
Low · Change unavailable
KEVNot listedNot listed by any tracked catalog.
RansomwareNot flaggedNo ransomware use recorded.
Public exploits1github

Timeline

  1. 26-09-2026
    PublishedVulnerability first disclosed.
  2. 28-09-2026
    Last modifiedVulnerability information updated.

Description

vLLM versions 0.22.0 through 0.23.0 fail to validate stop_token_ids against vocabulary bounds in Rust HTTP and gRPC frontends, allowing out-of-vocabulary token IDs to reach MinTokensLogitsProcessor. Attackers can submit requests with min_tokens greater than zero and out-of-vocabulary stop_token_ids to trigger CUDA tensor indexing failures that leave EngineCore in a fatal state requiring service restart.

CVSS metrics

5 scores · 3 sources · 2 versions

EPSS trend

Probability

0.36%

Chance of exploitation in the next 30 days

Percentile

29%

Versus all other CVEs

30-day change

Change unavailable

Change unavailable

27-09-202622-10-2026

Known exploited

Compare KEV catalogs
CISA KEV

Not in the CISA KEV catalog.

ENISA CNW

Not in the ENISA CNW catalog.

CIRCL

Not in the CIRCL catalog.

Public exploits

1 found
  • githubUnverified

    Vllm

    Maturity: poc

Weaknesses

CWE · root cause

Affected systems

PyPI1 product
  • vllm≥ 0.22.0, < 0.24.0
Vllm1 product
  • vllm≥ 0.22.0, < 0.24.0
Vllm-project1 product
  • vllm≥ 0.22.0, < 0.24.0

3 vendors · 3 products

References

2 links