Veille CVE
CVE-2026-93841
5.3 MoyenneDescription
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.
Produits concernés
Scores CVSS
| Version | Score | Source | Vecteur |
|---|---|---|---|
| 4.0 | 6.3 Moyenne | disclosure@vulncheck.com | 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
| 3.1 | 3.7 Faible | disclosure@vulncheck.com | CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:N |
| 3.1 | 5.3 Moyenne | nvd@nist.gov (NVD) | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:L/A:N |
Faiblesses (CWE)
Références
- https://github.com/vllm-project/vllm Product
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L241-L255 Product
- https://github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L33-L37 Product
- https://github.com/vllm-project/vllm/pull/49081 Issue TrackingPatch
- https://www.vulncheck.com/advisories/vllm-through-0.29.0-adjacent-request-sampler-state-corruption-via-unvalidated-prompt-token-ids Third Party Advisory