---
cve: "CVE-2026-93989"
severity: "LOW"
cvss: 2.3
epss: "2.2%"
vendor: "vllm-project"
kev: false
exploited: false
published: "2026-09-19 23:17:10"
tags: [cve, security, low]
source: tsecurity.de CVE-Dossier
exported: "2026-09-21T05:13:38+02:00"
---

# CVE-2026-93989

> 2.3 LOW · 🧪 PoC

## Beschreibung

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.

## CVSS-Vektor

```
CVSS:4.0/AV:N/AC:H/AT:P/PR:L/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N
```

| Metrik | Wert | Bewertung |
|---|---|---|
| AV Angriffsvektor | Netzwerk | bad |
| AC Komplexität | Hoch | good |
| PR Privilegien | Gering | warn |
| UI Interaktion | Keine | bad |

## Patch verfügbar (OSV)

- 98dff2a81d747d1dba01a47f939f48c3526d4206 (Commit)

## Referenzen

- <https://github.com/vllm-project/vllm/pull/48824>
- <https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/v1/worker/gpu/sample/bad_words.py>
- <https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/sampling_params.py#L694-L753>
- <https://github.com/vllm-project/vllm>
- <https://www.vulncheck.com/advisories/vllm-through-0.29.0-cross-request-logits-corruption-via-bad-words>

---
_Exportiert aus dem [tsecurity.de CVE-Dossier](https://tsecurity.de/cve?cve=CVE-2026-93989) · Datenquellen: EUVD (ENISA), NVD, OSV, CISA KEV, FIRST EPSS, Exploit-DB, BSI BITS_