Vllm
CVE-2025-62372
HIGH
GHSA-pmqf-x6x8-p7qw
Vulnerability Assessment
| Weakness |
CWE
OWASP Top 10:2025
A05:2025 - Injection
ASVS 5.0
V2 - Validation and Business Logic Array index validation
|
| Impact | CVSS score of 8.3 (HIGH). Attack characteristics: network attack vector, low complexity, low privileges required, no user interaction not required. EPSS exploitation probability: 0.08%. |
| Exploit ScenarioDerived | This vulnerability can be exploited remotely over the network. Successful exploitation could compromise the high-severity affected system. |
Get an e-mail when this CVE is exploited, patched or re-scored. Free account.
Alert meAnalysisAIv1 – Mar 28, 2026
vLLM is an inference and serving engine for large language models (LLMs). Rated high severity (CVSS 8.3), this vulnerability is remotely exploitable, low attack complexity.
RemediationAI
A vendor patch is available. Apply the latest security update as soon as possible. Apply vendor patches when available. Implement network segmentation and monitoring as interim mitigations.
Affected Packages
Source: OSV (Open Source Vulnerabilities)
Affects your stack
Affects 1 package in pypi
Checking this CVE against your own stacks and servers is part of the Basic plan and up.
Technical ContextAI · show details
This vulnerability is classified under CWE-129. vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1. Affected products include: Vllm. Version information: version 0.5.5.
Know when Vllm gets its next vulnerability
- Watch products and get an email when something new is published
- Check this CVE against your own stack and servers
- Exploit and PoC references, threat intelligence from 22 sources
No credit card · 7-day full trial
Severity by source
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:H
Primary rating from Vendor (github).
CVSS VectorVendor: github
Lifecycle Timeline
2DescriptionCVE.org
vLLM is an inference and serving engine for large language models (LLMs). From version 0.5.5 to before 0.11.1, users can crash the vLLM engine serving multimodal models by passing multimodal embedding inputs with correct ndim but incorrect shape (e.g. hidden dimension is wrong), regardless of whether the model is intended to support such inputs (as defined in the Supported Models page). This issue has been patched in version 0.11.1.
Executive ViewAI
Organizations using vLLM face notable risk from CVE-2025-62372 rated CVSS 8.3. Successful exploitation could significantly impact the confidentiality, integrity, or availability of affected systems. A patch is available and should be applied as part of regular vulnerability management.
Apply vendor patch. If immediate patching is not feasible: (1) Implement network-level access controls to limit exposure; (2) Enable enhanced monitoring and alerting; (3) Apply principle of least privilege.
Threat Intelligence Overview
NVD
CVE.org
EPSS
How this decision was reached
The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.
What every action level means
SSVC AssessmentENISA
Priority Score
Attack Technique
Denial of Service attacks render applications or systems unavailable by overwhelming resources or triggering failure conditions.
Affected Products (CPE)CVE.org
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Rated critical severity (CVSS 10.0
vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. Rated critical sev
Information exposure in vLLM inference engine versions 0.8.3 to before 0.14.1. Invalid image requests to the multimodal
Timing-based API key recovery in vLLM before 0.11.0rc2 can let remote attackers bypass bearer-token authentication on de
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Rated high severity (CVSS 7.5), th
Denial of service in the vLLM LLM inference server (all versions prior to 0.24.0) allows a remote client to crash the sh
vLLM before version 0.14.1 contains a server-side request forgery vulnerability in the MediaConnector class where incons
Out-of-memory worker crashes in vLLM can be induced by a single small compressed audio payload submitted to the /v1/chat
vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Rated medium severity (CVSS 6.5),
GPU memory exhaustion in vLLM versions prior to 0.28.0 lets an attacker with low-privileged API access (PR:L in the CVSS
Multimodal inference requests to vLLM deployments running versions prior to 0.28.0 can trigger a process-level assertion
Uncontrolled resource consumption in vLLM's OpenAI-compatible completions endpoint allows any authenticated API client t
Exploit-DB