PT-2026-123022
CVE-2026-116181
·
Published
2026-10-25
·
Updated
2026-10-25
Description by
CVSS 3.1
6.5
MediumMetricsAV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
vLLM from 0.20.1 before 0.29.0 contains an improper input validation vulnerability that allows remote attackers to crash the engine by supplying out-of-vocabulary stop token ids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or write outside the V2 runner's logits buffer.
Found an issue in the description? Have something to add? Feel free to write us 👾