CVE-2026-93989

EUVD-2026-83617
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.
ProviderTypeBase ScoreAtk. VectorAtk. ComplexityPriv. RequiredVector
NISTPrimary
3.1 LOW
NETWORK
HIGH
LOW
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N
Base Score
CVSS 3.x
EPSS Score
Percentile: 10.25%
Affected Products (NVD)
VendorProductVersion
vllmvllm
𝑥
≤ 0.29.0
𝑥
= Vulnerable software versions
Common Weakness Enumeration
References
https://github.com/vllm-project/vllm
https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/sampling_params.py#L694-L753
https://github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f48c3526d4206/vllm/v1/worker/gpu/sample/bad_words.py
https://github.com/vllm-project/vllm/pull/48824
https://www.vulncheck.com/advisories/vllm-through-0.29.0-cross-request-logits-corruption-via-bad-words