Description
vLLM from 0.8.5 before 0.31.0 has a denial of service flaw. LogprobsTensors.empty_cpu() in vllm/v1/outputs.py allocates an uninitialized int32 tensor, and the V1 model runner leaves prompt positions reported as computed by a KV connector unwritten. A client sharing the engine can send prompt_logprobs (or echo with logprobs) against a connector-cached prefix, making tokenizer decode raise OverflowError, which crashes EngineCore and drops all co-tenant requests.
Affected products
vllm: vllm
References2
- github.com/vllm-project/vllm/security/advisories/GHSA-rhcx-5729… MitigationVendor Advisory
- www.vulncheck.com/advisories/vllm-from-0.8.5-before-0.31.0-cros… Third Party Advisory
Metrics
- CVSS 3.1
-
7.7
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/A:H - CVSS 4.0
-
8.3
HIGH
Score source: CNA
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H/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: 17 · as of 8 November 2026
- CWE
- CWE-908
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.