CVE-2026-93841
vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs
- State
- Published
- Severity
- 6.3 Medium
- Published
- Sep 18, 2026
- Updated
- Sep 24, 2026
- Reserved
- Sep 18, 2026
Description
vLLM through 0.29.0 contains a memory corruption vulnerability in the Triton _bincount_kernel where prompt token IDs index the penalty prompt-presence bitset without bounds checking against vocabulary size. Attackers can submit multimodal audio requests with tokens equal to vocabulary size, causing out-of-bounds writes that corrupt concurrent requests' sampler state and alter repetition penalty behavior.
Scores
| CVSS | Score | Vector | Source |
|---|---|---|---|
| 4.0 | 6.3 Medium | CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:L/VA:N/SC:N/SI:N/SA:N | VulnCheck |
| 3.1 | 3.7 Low | CVSS:3.1/AV:N/AC:H/PR:N/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
- https://github.com/vllm-project/vllm/pull/49081patchissue-tracking
- https://github.com/vllm-project/vllmproduct
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L241-L255technical-description
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L33-L37technical-description
- VulnCheck Advisory: vLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDsthird-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.