CVE Professor
›
Back
CVE-2026-115914

CVE-2026-115914 — Vllm Vllm (tüm Sürümler) — CWE-617

MEDIUM CVSS 6.5 NVD

CVE-2026-115914 is a MEDIUM severity security vulnerability (CWE-617) (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. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited-OCR image path allows a remote client that can reach the OpenAI-compatible API to submit a legal image whose normalized pixels sum to zero when that image is alone in its per-step encoder batch. _parse_and_validate_image_input returns no embedding, embed_multimodal propagates that value, and sanity_check_mm_encoder_outputs triggers a fatal assertion that shuts down the engine for all users. 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-2026-115914
CVSS 6.5/10 · MEDIUM · 26.10.2026
CWE: CWE-617
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. From 0.11.1 until 0.32.0, the DeepSeek-OCR, DeepSeek-OCR-2, and Unlimited-OCR image path allows a remote client that can reach the OpenAI-compatible API to submit a legal image whose normalized pixels sum to zero when that image is alone in its per-step encoder batch. _parse_and_validate_image_input returns no embedding, embed_m…
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-617
Affected Products (1)
vllm:vllm (tüm sürümler)
References & Advisories (4)
github.com patch
github.com patch
github.com patch advisory
Related CVEs
4.8
CVE-2026-130669
ImageMagick before 7.1.2-35 contains a null pointer dereference vulnerability that allows attackers to crash t
6.8
CVE-2026-129860
Microsoft jxrlib through 1.1 and the mircomir jxrlib fork before 1.3.7 contain a reachable assertion vulnerabi
5.3
CVE-2026-85098
A reachable assertion vulnerability in the synoscgi in Synology DiskStation Manager (DSM) before 7.3.2-86009-5
5.3
CVE-2026-120980
On affected platforms running Arista EOS with VPLS-BGP enabled, an attacker who has established a BGP session
5.5
CVE-2026-125187
FFmpeg through 9.0.2 contains a reachable assertion vulnerability in the TTA encoder's tta_encode_frame() in l
5.5
CVE-2026-125238
FFmpeg through 9.0.2 contains a reachable assertion vulnerability in libxevd_receive_frame() in libavcodec/lib