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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2026-55646— vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size limit

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 0.22.0版本至0.24.0之前版本存在资源管理错误漏洞，该漏洞源于在处理/v1/audio/transcriptions和/v1/audio/transcriptions和/v1/audio/translations路由时，调用request.file.read()在检查上传文件大小限制前将音频文件完全加载到内存，可能导致攻击者通过提交超大文件造成内存压力或进程终止。

CVSS 6.5 · Medium EPSS 0.52% · P42

Affected Version Matrix 1

VendorProduct Version RangeStatus
vllm-project vllm >= 0.22.0, < 0.24.0 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-55646

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 speech-to-text endpoints allocate full upload before enforcing the audio file-size limit
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM is an inference and serving engine for large language models. From 0.22.0 to 0.23.0, the /v1/audio/transcriptions and /v1/audio/translations routes call request.file.read() to fully materialize an uploaded audio file into memory before vLLM checks the documented VLLM_MAX_AUDIO_CLIP_FILESIZE_MB compressed upload size limit (default 25 MB) later in the speech-to-text preprocessing step, so an API caller who can reach those routes can submit an oversized multipart upload and cause vLLM to allocate memory proportional to the uploaded file size before the request is rejected as too large, creating memory pressure or terminating the process depending on deployment resource limits. This issue is fixed in version 0.24.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
未加控制的资源消耗(资源穷尽)
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 资源管理错误漏洞
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 0.22.0版本至0.24.0之前版本存在资源管理错误漏洞，该漏洞源于在处理/v1/audio/transcriptions和/v1/audio/transcriptions和/v1/audio/translations路由时，调用request.file.read()在检查上传文件大小限制前将音频文件完全加载到内存，可能导致攻击者通过提交超大文件造成内存压力或进程终止。
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 >= 0.22.0, < 0.24.0 -

II. Public POCs for CVE-2026-55646

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

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-55646

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-55646 (2)

Vendor Advisories for CVE-2026-55646 (1)

Same Patch Batch · vllm-project · 2026-07-06 · 4 CVEs total

CVE-2026-54234 7.5 HIGH vLLM: Remote DoS in vLLM via Invalid Recovered Token Reinjection
CVE-2026-55514 vLLM denial of service via prompt embeds on M-RoPE models
CVE-2026-55574 vLLM: ReDoS via structured_outputs.regex compiled without timeout in xgrammar and outlines

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-400

V. Comments for CVE-2026-55646

No comments yet

Leave a comment