Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🛡️
Not in CISA KEV
MEDIUM severity

CVE-2026-100652 — Vllm-project

MEDIUM

CVE-2026-100652 is a medium-severity (CVSS 5.9) Improper Input Validation vulnerability. No vendor fix is recorded yet; mitigation options are listed below.

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.…

Published
Updated
Affected
1 product
Patched
See advisory
Exploits
None indexed
Exploitation data as of Oct 6, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

  • CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-100652.

EPSS Exploitation Probability

via FIRST.org ↗
0.3%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs24th percentile — riskier than 24% of all scored CVEsHighest risk
0.00%0.28%0.55%0.83%0.3%0.3%Oct 26Oct 26

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

CVE-2026-100652 by exploitation likelihood (EPSS) against impact (CVSS). Outside the shaded patch-first corner.

Where this sits among everything scored

Of 383,485 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Counts from FIRST.org, log-scaled.

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.

Affected Products

1 product · 1 configurations
Application
vllmvllm
≥ 0.22.0 && < 0.24.0
range

Detection & mitigation playbook

Vulnerability
  1. Detect

    Identify every host running the affected component and compare the installed build against the fixed version below — for source-built or distro-packaged software the version string, not a lockfile, is the source of truth (`dpkg -l`, `rpm -q`, or the binary's own `--version`).

  2. Remediation status

    No fixed release is recorded for CVE-2026-100652 yet. Track the upstream advisory, and apply the exposure-reduction steps below in the meantime.

  3. Mitigate without a patch

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

Frequently Asked Questions

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.
O3 Security · Impact-Aware SCA

Is CVE-2026-100652 in your dependencies?

Find it across , including transitive dependencies.

CVE-2026-100652: Vllm-project (Medium 5.9) | O3 Security