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
CVE-2026-100652 is a medium-severity flaw (CVSS 5.9) affecting vllm. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.
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.
Why this priority
- Public exploit reference
- Remotely exploitable, no login, no user action
A fixed release or distro patch exists.
Risk facts
| CVSS score | 5.9 (Medium) |
| Attack vector | Network (remote) |
| Attack complexity | High |
| Privileges needed | None |
| User interaction | None |
| EPSS exploit chance | 0.4% (top 64%) |
| CISA exploited list | No |
| Weakness | CWE-20 |
| Published | 2026-09-26 |
| Last modified | 2026-10-06 |
Last updated 2026-10-06 · Sources: CVE Program, NVD, CISA KEV, EPSS and vendor advisories · How we score
Am I affected?
Timeline
- Published CVE record published
- Updated Record last modified
Scores and fixes here are computed automatically from those and other public sources. Confirm with the vendor advisory before changing production systems.
Quick answers
How do I fix CVE-2026-100652?
vllm: upgrade to 0.24.0. Exact commands for each OS are on this page.
Is CVE-2026-100652 being exploited?
CVE-2026-100652 is not on the CISA Known Exploited Vulnerabilities list at the time of the last update. Check again, as this can change.
What does CVE-2026-100652 affect?
CVE-2026-100652 affects vllm. Severity is medium (CVSS 5.9). 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_to
How urgent is CVE-2026-100652?
Priority 40/100. Public exploit reference; Remotely exploitable, no login, no user action
Related CVEs
- CVE-2026-5497 HIGH 7.5 UPGRADE vLLM versions 0.8.0 and later are vulnerable to an Out-of-Memory (OOM) Denial of Service (DoS) attack due to u
- CVE-2026-48746 CRITICAL 9.1 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54232 HIGH 8.8 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-41523 HIGH 7.5 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)
- CVE-2026-54236 MEDIUM 5.3 UPGRADE vLLM is an inference and serving engine for large language models (LLMs)