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

Goal: 1000 CNY · Raised: 1336 CNY

100%
Buy Us a Coffee

CVE-2025-24357— vLLM allows a malicious model RCE by torch.load in hf_model_weights_iterator

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 v0.7.0之前版本存在代码问题漏洞，该漏洞源于当torch.load加载恶意pickle数据时，会在unpickling期间执行任意代码。

CVSS 7.5 · High EPSS 0.71% · P50

Possible ATT&CK Techniques 1 AI

T1059 · Command and Scripting Interpreter
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2025-24357

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Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.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 allows a malicious model RCE by torch.load in hf_model_weights_iterator
Source: CVE Program / CVE List V5
Vulnerability Description
vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in v0.7.0.
Source: CVE Program / CVE List V5
CVSS Information
CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
Source: CVE Program / CVE List V5
Vulnerability Type
可信数据的反序列化
Source: CVE Program / CVE List V5
Vulnerability Title
vLLM 代码问题漏洞
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 v0.7.0之前版本存在代码问题漏洞，该漏洞源于当torch.load加载恶意pickle数据时，会在unpickling期间执行任意代码。
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 < 0.7.0 -

II. Public POCs for CVE-2025-24357

# POC Description Source Link Shenlong Link
AI-Generated POC Premium
Qwen3.6-35B-A3B · 6441 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-2025-24357

请登录查看更多情报信息。

Patches & Fixes for CVE-2025-24357 (2)

Vendor Advisories for CVE-2025-24357 (1)

Vendor Pages for CVE-2025-24357 (1)

IV. Related Vulnerabilities

Same product: vllm
Same vendor: vllm-project
Same weakness: CWE-502

V. Comments for CVE-2025-24357

No comments yet

Leave a comment