vLLM up to 0.6.x weight_utils.py weights_only deserialization

CVSS Meta Temp Score
CVSS is a standardized scoring system to determine possibilities of attacks. The Temp Score considers temporal factors like disclosure, exploit and countermeasures. The unique Meta Score calculates the average score of different sources to provide a normalized scoring system.
Current Exploit Price (≈)
Our analysts are monitoring exploit markets and are in contact with vulnerability brokers. The range indicates the observed or calculated exploit price to be seen on exploit markets. A good indicator to understand the monetary effort required for and the popularity of an attack.
CTI Interest Score
Our Cyber Threat Intelligence team is monitoring different web sites, mailing lists, exploit markets and social media networks. The CTI Interest Score identifies the interest of attackers and the security community for this specific vulnerability in real-time. A high score indicates an elevated risk to be targeted for this vulnerability.
7.0$0-$5k0.00

Summaryinfo

A vulnerability was found in vLLM up to 0.6.x. It has been declared as problematic. Affected is an unknown function of the file vllm/model_executor/weight_utils.py. Such manipulation of the argument weights_only leads to deserialization. This vulnerability is referenced as CVE-2025-24357. It is possible to launch the attack remotely. No exploit is available. It is recommended to upgrade the affected component.

Detailsinfo

A vulnerability, which was classified as problematic, has been found in vLLM up to 0.6.x. Affected by this issue is some unknown processing of the file vllm/model_executor/weight_utils.py. The manipulation of the argument weights_only with an unknown input leads to a deserialization vulnerability. Using CWE to declare the problem leads to CWE-502. The product deserializes untrusted data without sufficiently verifying that the resulting data will be valid. Impacted is confidentiality, integrity, and availability. CVE summarizes:

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.

The advisory is shared for download at github.com. This vulnerability is handled as CVE-2025-24357 since 01/20/2025. The exploitation is known to be difficult. The attack may be launched remotely. No form of authentication is required for exploitation. Successful exploitation requires user interaction by the victim. There are known technical details, but no exploit is available.

Upgrading to version 0.7.0 eliminates this vulnerability.

The vulnerability is also documented in the vulnerability database at EUVD (EUVD-2025-0192). VulDB is the best source for vulnerability data and more expert information about this specific topic.

Productinfo

Name

Version

CPE 2.3info

CPE 2.2info

CVSSv4info

VulDB Vector: 🔍
VulDB Reliability: 🔍

CVSSv3info

VulDB Meta Base Score: 7.1
VulDB Meta Temp Score: 7.0

VulDB Base Score: 5.0
VulDB Temp Score: 4.8
VulDB Vector: 🔍
VulDB Reliability: 🔍

NVD Base Score: 8.8
NVD Vector: 🔍

CNA Base Score: 7.5
CNA Vector (GitHub_M): 🔍

CVSSv2info

AVACAuCIA
💳💳💳💳💳💳
💳💳💳💳💳💳
💳💳💳💳💳💳
VectorComplexityAuthenticationConfidentialityIntegrityAvailability
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock

VulDB Base Score: 🔍
VulDB Temp Score: 🔍
VulDB Reliability: 🔍

Exploitinginfo

Class: Deserialization
CWE: CWE-502 / CWE-20
CAPEC: 🔍
ATT&CK: 🔍

Physical: No
Local: No
Remote: Yes

Availability: 🔍
Status: Not defined

EPSS Score: 🔍
EPSS Percentile: 🔍

Price Prediction: 🔍
Current Price Estimation: 🔍

0-DayUnlockUnlockUnlockUnlock
TodayUnlockUnlockUnlockUnlock

Threat Intelligenceinfo

Interest: 🔍
Active Actors: 🔍
Active APT Groups: 🔍

Countermeasuresinfo

Recommended: Upgrade
Status: 🔍

0-Day Time: 🔍

Upgrade: vLLM 0.7.0

Timelineinfo

01/20/2025 🔍
01/27/2025 +7 days 🔍
01/27/2025 +0 days 🔍
06/28/2025 +152 days 🔍

Sourcesinfo

Advisory: github.com
Status: Confirmed

CVE: CVE-2025-24357 (🔍)
GCVE (CVE): GCVE-0-2025-24357
GCVE (VulDB): GCVE-100-293600
EUVD: 🔍

Entryinfo

Created: 01/27/2025 19:01
Updated: 06/28/2025 06:05
Changes: 01/27/2025 19:01 (63), 02/08/2025 16:28 (3), 06/28/2025 04:22 (1), 06/28/2025 06:05 (12)
Complete: 🔍
Cache ID: 216::103

VulDB is the best source for vulnerability data and more expert information about this specific topic.

Discussion

No comments yet. Languages: en.

Please log in to comment.

◂ PreviousOverviewNext ▸

Do you want to use VulDB in your project?

Use the official API to access entries easily!