Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-90553— vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor

Quick assessment

Affected
vllm-project vLLM
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.28.0之前版本存在代码注入漏洞，该漏洞源于LlavaOnevision2处理器加载器在加载远程处理器类时忽略trust_remote_code参数，攻击者可构造在processing_llava_onevision2.py中包含任意代码的恶意模型，即使trust_remote_code设置为False也会以vLLM进程权限执行任意代码。

CVSS 7.8 · High EPSS 0.31% · P22

Affected Version Matrix 2

VendorProduct Version RangeStatus
vllm-project vLLM < 0.28.0 affected
0.28.0 unaffected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-90553

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
对生成代码的控制不恰当(代码注入)
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 代码注入漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
vLLM是vLLM团队开源的一个适用于 LLM 的高吞吐量和内存高效推理和服务引擎。 vLLM 0.28.0之前版本存在代码注入漏洞，该漏洞源于LlavaOnevision2处理器加载器在加载远程处理器类时忽略trust_remote_code参数，攻击者可构造在processing_llava_onevision2.py中包含任意代码的恶意模型，即使trust_remote_code设置为False也会以vLLM进程权限执行任意代码。
Source: CNNVD (China National Vulnerability Database)
CVSS Information
N/A
Source: CNNVD (China National Vulnerability Database)
Vulnerability Type
N/A
Source: CNNVD (China National Vulnerability Database)

Affected Products

Vendor Product Affected Versions CPE Subscribe
vllm-project vLLM 0 ~ 0.28.0 -

II. Public POCs for CVE-2026-90553

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-90553

请登录查看更多情报信息。

Vendor Advisories for CVE-2026-90553 (2)

Same Patch Batch · vllm-project · 2026-09-12 · 3 CVEs total

CVE-2026-90555 6.5 MEDIUM vLLM before 0.28.0 Denial of Service via Audio Header
CVE-2026-90554 6.2 MEDIUM vLLM before 0.28.0 Denial of Service via audio extraction

IV. Related Vulnerabilities

Same product: vLLM
Same vendor: vllm-project
Same weakness: CWE-94

V. Comments for CVE-2026-90553

No comments yet

Leave a comment