CVE-2026-116181
6.5 MEDIUMpublic exploit availablePublished 2026-10-25 · Updated 2026-10-26
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD description
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Weaknesses
CWE-129
Public exploit & PoC references
All references
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- HIGHCVE-2024-58400PoC
- MEDIUMCVE-2026-100654PoC
- MEDIUMCVE-2026-100836PoC
- UNSCOREDCVE-2026-102510
- UNSCOREDCVE-2026-102511
- LOWCVE-2026-102822PoC
- MEDIUMCVE-2026-103220
- HIGHCVE-2026-103672PoC
Related by shared AI tags and CWE weakness class. Browse the full archive.