CVE-2026-116181
mediumvLLM 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-vocabul…
Vendor / product: Vllm — vllm
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
6.5
6.5 (CVSS v3.1)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H Severity source: NVD CVSS v3.1 (disclosure@vulncheck.com)
Timeline (UTC)
Published: 2026-10-25 14:16
Modified: 2026-10-29 20:17
NVD status: Analyzed
Last synced 3 hours ago
Verified against the source API 2026-10-29 20:26 UTC
Exploitation
Not listed in CISA KEV (as of last catalog sync)
Absence from KEV does not mean a CVE is not exploited. Exploitation status: unknown (no authoritative evidence in our sources).
Affected products
vllm / vllm ≥0.20.1 <0.29.0
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
Patch / mitigation: https://github.com/vllm-project/vllm/security/advisories/GHSA-w9r6-29q4-pvpr
References
- https://github.com/vllm-project/vllm/security/advisories/GHSA-w9r6-29q4-pvpr disclosure@vulncheck.com
- https://www.vulncheck.com/advisories/vllm-0.20.1-before-0.29.0-dos-and-gpu-out-of-bounds-w... disclosure@vulncheck.com
Data sources
NVD CVE API 2.0 — fetched 2026-10-29 20:26 UTC · record ↗