CVE-2026-93989
vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words
- State
- Published
- Severity
- 2.3 Low
- Published
- Sep 19, 2026
- Updated
- Sep 22, 2026
- Reserved
- Sep 19, 2026
Description
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.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 2.3 Low | 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 | VulnCheck |
| 3.1 | 3.1 Low | CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N | VulnCheck |
Weaknesses
- CWE-129 Improper Validation of Array Index
Affected Products
| Product | Versions |
|---|---|
vllmvllm-project |
|
References
- GitHub PR #48824issue-trackingpatch
- _bad_words_kernel at v0.29.0technical-description
- update_from_tokenizer at v0.29.0technical-description
- https://github.com/vllm-project/vllmproduct
- VulnCheck Advisory: vLLM through 0.29.0 Cross-Request Logits Corruption via bad_wordsthird-party-advisory
Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.