CVE Professor
›
Back
CVE-2026-115916

CVE-2026-115916 — Vllm Vllm (tüm Sürümler) — CWE-129 · CWE-193

MEDIUM CVSS 6.5 NVD

CVE-2026-115916 is a MEDIUM severity security vulnerability (CWE-129, CWE-193) (CVSS 6.5/10) affecting Vllm Vllm (tüm Sürümler). Technical vector analysis shows that an attacker can exploit this flaw remotely over the network with low-privileged access (PR:L) with zero user interaction (UI:N), causing high-impact service disruption (A:H).

📄 Official NVD / MITRE Original Record Text

vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses it, causing a CUDA device-side assertion and terminating the engine. This issue is fixed in version 0.32.0.

Published 26.10.2026
ISO Date 2026-10-26
CVSS Version v3.1
Source NVD
CVSS v3.1 Vector Metrics
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Attack Vector Network AV:N
Attack Complexity Low AC:L
Privileges Req. Low PR:L
User Interaction None UI:N
Scope Unchanged S:U
Confidentiality None C:N
Integrity None I:N
Availability High A:H
AI Security Analysis & Remediation
🤖 Generating Deep AI Security Analysis…
Analyzing CVSS vector & CWE weakness structure…

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
CVE-2026-115916
CVSS 6.5/10 · MEDIUM · 26.10.2026
CWE: CWE-129, CWE-193
Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

🎯 WHAT IS THIS VULNERABILITY?
Summary: vLLM is an inference and serving engine for large language models. Prior to 0.32.0, vllm/tokenizers/hf.py computes max_token_id with an off-by-one upper bound, allowing a pre-tokenized prompt ID equal to the vocabulary size to pass validation. For a tensor-parallel size of one and an exact multiple-of-64 vocabulary, VocabParallelEmbedding.forward does not mask that value before F.embedding uses…
Affected: vllm:vllm

⚡ ATTACK CHAIN
Remotely over internet | low-privilege account | no user interaction | low complexity.

🌍 REAL WORLD IMPACT
Service can be completely taken down.

🛡️ REMEDIATION
→ Apply vendor security update for vllm:vllm.
→ Add WAF rule, create IDS alert for anomalous traffic.

⚠️ URGENCY
📋 Routine update cycle (30 days)

────────────────────────────────────────
[Kural Tabanlı Otomatik Güvenlik Analizi]

Target Reconnaissance Queries (FOFA & Shodan)

FOFA Query

app="vllm vllm"
CVSS Score
6.5 / 10 · CVSS MEDIUM
Weakness Types (CWE)
CWE-129 CWE-193
Affected Products (1)
vllm:vllm (tüm sürümler)
References & Advisories (4)
github.com patch
github.com patch
github.com patch advisory
Related CVEs
7.8
CVE-2026-132150
A flaw was found in the file-xmc plugin in GIMP. When processing a specially crafted XMC image file, the plugi
7.1
CVE-2026-122042
WarehousePG (WHPG) 6.27.1 through 6.27.7 and 7.2.1 through 7.6.1 are affected by an out-of-bounds write vulner
7.0
CVE-2026-109151
In the Matter and Aliro Door Lock Application of the Nordic Semiconductor nRF Door Lock and Access Control Add
6.5
CVE-2026-130386
Contiki-NG through 5.2 contains an out-of-bounds access vulnerability in buffer_reclaim() and domain_set_free(
3.7
CVE-2026-128846
@fastify/busboy is a streaming parser for multipart form data used by Fastify. In versions 3.2.1 through 3.2.5
0.0
CVE-2026-129114
JSON::XS versions from 3.04 before 4.05 for Perl write one byte past a heap buffer when appending a one-byte c