Description
vLLM versions before 0.28.0 fail to validate the lower bound of token IDs in the /v1/embeddings and /pooling endpoints, allowing unauthenticated attackers to crash the engine by submitting negative token IDs. A single request with a negative token ID triggers a CUDA device-side assertion that poisons the GPU context, causing all subsequent requests to fail until the process restarts.
Affected products
vllm: vllm
References3
- github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm… ExploitMitigationPatchVendor Advisory
- github.com/vllm-project/vllm/security/advisories/GHSA-25q3-v2hm… ExploitMitigationPatchVendor Advisory
- www.vulncheck.com/advisories/vllm-before-0.28.0-denial-of-servi… Third Party Advisory
Metrics
- CVSS 3.1
-
7.5
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H - CVSS 4.0
-
8.7
HIGH
Score source: CNA
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/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
- 1% percentile: 46 · 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.