Description
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.
Affected products
vllm: vllm
References5
- github.com/vllm-project/vllm/pull/48824 Issue TrackingPatch
- github.com/vllm-project/vllm Product
- github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f4… Product
- github.com/vllm-project/vllm/blob/98dff2a81d747d1dba01a47f939f4… Product
- www.vulncheck.com/advisories/vllm-through-0.29.0-cross-request-… Third Party Advisory
Metrics
- CVSS 3.1
-
4.3
MEDIUM
Score source: NVD
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:L/A:N - CVSS 4.0
-
2.3
LOW
Score source: CNA
CVSS:4.0/AV:N/AC:H/AT:P/PR:L/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 - EPSS — exploit probability
- 0% percentile: 10 · as of 8 November 2026
- CWE
- CWE-129
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.