Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions before 0.29.0 validate allowed_token_ids against the tokenizer length rather than the model's output logits width. An attacker who can send requests can supply token IDs above the output vocabulary that pass validation, which can corrupt GPU logits state and let concurrent requests sample tokens outside their allowlists. Upgrade vllm to 0.29.0 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 0.0025, the 15th 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-2026-3998
- github.com/vllm-project/vllm/blob/v0.28.0/vllm/sampling_params.py#L881-L903
- github.com/vllm-project/vllm/blob/v0.28.0/vllm/v1/worker/gpu/sample/logit_bias.py#L179-L191
- www.vulncheck.com/advisories/vllm-before-0.29.0-cross-request-logits-corruption-via-allowed-token-ids
- github.com/vllm-project/vllm/commit/5b0e5b69ac1a3884a6479c9537789c95263cc804
- github.com/vllm-project/vllm/pull/49080
- github.com/vllm-project/vllm