Improper input validation in Vllm
CVE-2026-100652
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.
Vulnerability class: Drupalgeddon 2 (CVE-2018-7600)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 5.9 (Medium). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS: 0.004 (36.6th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 37th percentile — 36.6% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.004 · newest: 0.004 · change: +0.001
Affected products
Weakness classification (CWE)
References
- GitHub Security Advisory (GHSA-qff2-492f-9fm4) (vendor-advisory, Exploit, Mitigation, Vendor Advisory)
- VulnCheck Advisory: vLLM 0.22.0 through 0.23.0 Denial of Service via stop_token_ids (Third Party Advisory, third-party-advisory)
Frequently asked questions
- What is CVE-2026-100652?
- CVE-2026-100652 is a medium-severity vulnerability in Vllm, classified under Improper Input Validation. CVSS score: 5.9/10. Published 2026-09-26.
- How severe is CVE-2026-100652?
- Medium severity. CVSS v3 base score is 5.9 out of 10.