vllm up to 0.7.1 hash constant integrity check

Summaryinfo

A vulnerability was found in vllm up to 0.7.1. It has been classified as problematic. The impacted element is the function hash. This manipulation of the argument constant causes integrity check. This vulnerability is tracked as CVE-2025-25183. The attack is possible to be carried out remotely. No exploit exists. Upgrading the affected component is recommended.

Detailsinfo

A vulnerability was found in vllm up to 0.7.1. It has been declared as problematic. Affected by this vulnerability is the function hash. The manipulation of the argument constant with an unknown input leads to a integrity check vulnerability. The CWE definition for the vulnerability is CWE-354. The product does not validate or incorrectly validates the integrity check values or "checksums" of a message. This may prevent it from detecting if the data has been modified or corrupted in transmission. As an impact it is known to affect integrity. The summary by CVE is:

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. Prefix caching makes use of Python's built-in hash() function. As of Python 3.12, the behavior of hash(None) has changed to be a predictable constant value. This makes it more feasible that someone could try exploit hash collisions. The impact of a collision would be using cache that was generated using different content. Given knowledge of prompts in use and predictable hashing behavior, someone could intentionally populate the cache using a prompt known to collide with another prompt in use. This issue has been addressed in version 0.7.2 and all users are advised to upgrade. There are no known workarounds for this vulnerability.

It is possible to read the advisory at github.com. This vulnerability is known as CVE-2025-25183 since 02/03/2025. The exploitation appears to be difficult. The attack can be launched remotely. It demands that the victim is doing some kind of user interaction. Technical details of the vulnerability are known, but there is no available exploit.

Upgrading to version 0.7.2 eliminates this vulnerability. Applying the patch 432117cd1f59c76d97da2eaff55a7d758301dbc7 is able to eliminate this problem. The bugfix is ready for download at github.com. The best possible mitigation is suggested to be upgrading to the latest version.

The vulnerability is also documented in the vulnerability database at EUVD (EUVD-2025-4074). Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Productinfo

Name

• vllm

Version

• 0.7.0
• 0.7.1

License

• open-source

CPE 2.3info

• 🔍
• 🔍

CPE 2.2info

• 🔍
• 🔍

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Discussion