PatchTheCVECVE-2026-93840: vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width i
CVE-2026-93840 is a low-severity flaw (CVSS 3.7) affecting vllm. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.
vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, causing LogitBiasState to corrupt GPU logits state and allow concurrent requests to sample tokens outside their allowlists.
Why this priority
- Remotely exploitable, no login, no user action
A fixed release or distro patch exists.
Risk facts
| CVSS score | 3.7 (Low) |
| Attack vector | Network (remote) |
| Attack complexity | High |
| Privileges needed | None |
| User interaction | None |
| EPSS exploit chance | 0.2% (top 84%) |
| CISA exploited list | No |
| Weakness | CWE-129 |
| Published | 2026-09-18 |
| Last modified | 2026-09-28 |
Last updated 2026-09-28 · 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-2026-93840?
vllm: upgrade to 0.29.0. Exact commands for each OS are on this page.
Is CVE-2026-93840 being exploited?
CVE-2026-93840 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-2026-93840 affect?
CVE-2026-93840 affects vllm. Severity is low (CVSS 3.7). vLLM before 0.29.0 validates allowed_token_ids against tokenizer length instead of model output logits width in SamplingParams._validate_allowed_token_ids(). Attackers can supply token IDs above the output vocabulary that pass validation, c
How urgent is CVE-2026-93840?
Priority 22/100. 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)