2.3
Low
CVE-2026-93989 vLLM through 0.29.0 fails to properly validate bad_words token indices against the model's generation output width in…
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.
Affected products and versions
| Product | Affected versions | Fixed in |
|---|---|---|
| vllm 0.29 | earliest → 0.29.0 | No fix stated |
References
- GitHub PR #48824 github.com
- _bad_words_kernel at v0.29.0 github.com
- update_from_tokenizer at v0.29.0 github.com
- github.com github.com
- VulnCheck Advisory: vLLM through 0.29.0 Cross-Request Logits Corruption via bad_words www.vulncheck.com
Timeline
- Published
- Last modified
Other CVEs of vllm
The 121 CVEs of vllm →
CVE-2026-115918
vLLM is an inference and serving engine for large language models
6.5
Medium
CVE-2026-115917
vLLM is an inference and serving engine for large language models
3.4
Low
CVE-2026-115916
vLLM is an inference and serving engine for large language models
6.5
Medium
CVE-2026-115915
vLLM is an inference and serving engine for large language models
8.1
High