CVE-2025-25183: vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Maliciously constructed statements can lead to hash collisions, ...

Description

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.

Metrics

CVSS 3.1

2.6/10

CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N

EPSS Probability

0.18%

7.3th percentile

Probability of exploitation in the next 30 days. Learn more

Weakness Enumeration

CWE-354

Affected Software

Vendor	Product	Versions
Vllm	Vllm	< 0.7.2

References

https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7Not Applicable
https://github.com/vllm-project/vllm/pull/12621Issue Tracking
https://github.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8Vendor Advisory

Timeline

Published: Feb 7, 2025
Last Modified: Jun 17, 2026
Status: Analyzed

Frequently Asked Questions

What is CVE-2025-25183?

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.

How severe is CVE-2025-25183?

CVE-2025-25183 has a CVSS score of 2.6/10 (LOW severity). The EPSS model estimates a 0.18% probability of exploitation in the next 30 days.

How do I fix CVE-2025-25183?

Check the vendor references and advisories linked above for patched versions and mitigation guidance. You can also run a Strix scan to test if your systems are affected.