PatchTheCVECVE-2026-93989: vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output w
CVE-2026-93989 is a low-severity flaw (CVSS 3.1) affecting vllm. Below: why it ranks where it does, which versions are affected, what to do, and the exact commands.
vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of concurrent requests, causing different in-flight HTTP requests to return incorrect tokens.
Why this priority
- No elevated risk signals yet
A fixed release or distro patch exists.
Risk facts
| CVSS score | 3.1 (Low) |
| Attack vector | Network (remote) |
| Attack complexity | High |
| Privileges needed | Low |
| User interaction | None |
| EPSS exploit chance | 0.2% (top 90%) |
| CISA exploited list | No |
| Weakness | CWE-129 |
| Published | 2026-09-19 |
| 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-2026-93989?
vllm: upgrade to newer than 0.29.0. Exact commands for each OS are on this page.
Is CVE-2026-93989 being exploited?
CVE-2026-93989 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-2026-93989 affect?
CVE-2026-93989 affects vllm. Severity is low (CVSS 3.1). vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in SamplingParams.update_from_tokenizer(). Attackers can supply out-of-bounds token indices that corrupt logits memory of con
How urgent is CVE-2026-93989?
Priority 13/100. No elevated risk signals yet.
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)