Lucene search
+L

9 matches found

NVD
NVD
•added 2026/10/25 2:16 p.m.•30 views

CVE-2026-116181

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 stoptokenids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or writ...

7.1CVSS0.00374EPSS
SaveExploits0References2
EUVD
EUVD
•added 2026/10/25 1:20 p.m.•19 views

EUVD-2026-109442

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 stoptokenids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or writ...

7.1CVSS6.1AI score0.00374EPSS
SaveExploits0References2
Cvelist
Cvelist
•added 2026/10/25 1:20 p.m.•40 views

CVE-2026-116181 vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids

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 stoptokenids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or writ...

7.1CVSS0.00374EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
•added 2026/10/25 1:20 p.m.•11 views

CVE-2026-116181 vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids

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 stoptokenids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or writ...

7.1CVSS6.1AI score0.00374EPSS
SaveExploits0References2
Mend
Mend
•added 2026/10/25 1:20 p.m.•27 views

CVE-2026-116181

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 stoptokenids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or writ...

7.1CVSS6.1AI score0.00374EPSS
SaveExploits0References2
CVE
CVE
•added 2026/10/25 1:20 p.m.•21 views

CVE-2026-116181

The vLLM library versions 0.20.1 before 0.29.0 are susceptible to an improper input validation vulnerability. Remote attackers can exploit this by supplying out-of-vocabulary stop_token_ids via OpenAI chat, completion, generate, or batch requests. This flaw can lead to a Denial of Service (DoS) b...

7.1CVSS6.1AI score0.00374EPSS
SaveExploits0References2Affected Software1
osv_cve
osv_cve
•added 2026/10/25 1:20 p.m.•44 views

CVE-2026-116181 vLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids

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 stoptokenids. Attackers can send OpenAI chat, completion, generate, or batch requests with invalid IDs to terminate the engine or writ...

7.1CVSS6.1AI score0.00374EPSS
SaveExploits0References4
CNNVD
CNNVD
•added 2026/10/25 12:00 a.m.•15 views

vLLM input validation error vulnerability

Versions vLLM 0.20.1 through 0.29.0 contain an input validation error vulnerability. This flaw stems from improper validation of stoptokenids. Remote attackers can exploit it by sending OpenAI chat, completion, generate, or batch requests containing invalid IDs, potentially causing the engine to...

7.1CVSS6.2AI score0.00374EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2026/10/25 12:00 a.m.•22 views

PT-2026-123022

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...

7.1CVSS6.1AI score0.00374EPSS
SaveExploits0References3
Rows per page
Query Builder