CVSS 7.1 (high) · published 2026-10-25
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.
Affected products (NVD): vllm vllm
Fixed in (NVD): 0.29.0
Weakness: CWE-129
Source: NVD CVE-2026-116181
Connect an AI agent to the FixLane MCP server or ask the Telegram bot to check what you have installed against incidents with a verified fixed version.