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

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

CVE-2025-62164— VLLM deserialization vulnerability leading to DoS and potential RCE

Quick assessment

Affected
vllm-project vllm
Exploitation
Public or AI PoC available; prioritize validation
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 0.10.2版本至0.11.1之前版本存在缓冲区错误漏洞，该漏洞源于Completions API端点存在内存损坏，可能导致崩溃或远程代码执行。

CVSS 8.8 · High EPSS 0.93% · P59
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2025-62164

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 deserialization vulnerability leading to DoS and potential RCE
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM is an inference and serving engine for large language models (LLMs). From versions 0.10.2 to before 0.11.1, a memory corruption vulnerability could lead to a crash (denial-of-service) and potentially remote code execution (RCE), exists in the Completions API endpoint. When processing user-supplied prompt embeddings, the endpoint loads serialized tensors using torch.load() without sufficient validation. Due to a change introduced in PyTorch 2.8.0, sparse tensor integrity checks are disabled by default. As a result, maliciously crafted tensors can bypass internal bounds checks and trigger an out-of-bounds memory write during the call to to_dense(). This memory corruption can crash vLLM and potentially lead to code execution on the server hosting vLLM. This issue has been patched in version 0.11.1.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
输入验证不恰当
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 缓冲区错误漏洞
Source: CNNVD (China National Vulnerability Database)
Vulnerability Description
vLLM是vLLM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 0.10.2版本至0.11.1之前版本存在缓冲区错误漏洞，该漏洞源于Completions API端点存在内存损坏，可能导致崩溃或远程代码执行。
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 >= 0.10.2, < 0.11.1 -

II. Public POCs for CVE-2025-62164

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 6072 chars
Pro+ exclusive includes:
Vulnerability reproduction recording (real sandbox build + trigger, exclusive)
In-depth vulnerability mechanism
Trigger conditions & impact
Full executable POC code
Exploit chain & mitigation
POC zip download
100+ AI POC generations per month

III. Intelligence Information for CVE-2025-62164

请登录查看更多情报信息。

Vendor Advisories for CVE-2025-62164 (1)

Same Patch Batch · vllm-project · 2025-11-21 · 3 CVEs total

CVE-2025-62426 6.5 MEDIUM vLLM vulnerable to DoS via large Chat Completion or Tokenization requests with specially c
CVE-2025-62372 vLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-20

V. Comments for CVE-2025-62164

No comments yet

Leave a comment