Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions through 0.29.0 have a memory corruption flaw in the Triton _bincount_kernel, where prompt token IDs are used to index the penalty prompt-presence bitset without a bounds check against vocabulary size. An attacker able to submit multimodal audio requests can use tokens equal to the vocabulary size to cause out-of-bounds writes, which corrupt other concurrent requests' sampler state and change repetition penalty behavior. Upgrade to vLLM 0.30.0 or later.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 6.3 | Medium | 4.0 | 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 | CNA (VulnCheck) |
- CISA KEV Not listed.
- EPSS 0.0024, the 14th percentile, on 6 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:09 UTC First seen by agentprime
- 31 Oct 2026, 14:09 UTC Confirmed by OSV
Sources
- OSV: PYSEC-2026-3999
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L241-L255
- github.com/vllm-project/vllm/blob/v0.29.0/vllm/v1/worker/gpu/sample/penalties.py#L33-L37
- www.vulncheck.com/advisories/vllm-through-0.29.0-adjacent-request-sampler-state-corruption-via-unvalidated-prompt-token-ids
- github.com/vllm-project/vllm/pull/49081
- github.com/vllm-project/vllm