PT-2025-6000 · Python+1 · Python+1
Kexinoh
·
Published
2025-02-06
·
Updated
2025-07-01
·
CVE-2025-25183
CVSS v3.1
2.6
Low
| Vector | AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N |
Name of the Vulnerable Software and Affected Versions
vLLM versions prior to 0.7.2
Description
Maliciously constructed statements can lead to hash collisions, resulting in cache reuse, which can interfere with subsequent responses and cause unintended behavior. The issue arises from the use of Python's built-in
hash() function, which as of Python 3.12, returns a predictable constant value for hash(None). This makes it more feasible for someone to exploit hash collisions. 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. The impact of a collision would be using cache that was generated using different content.Recommendations
For versions prior to 0.7.2, upgrade to version 0.7.2 or later to address the issue. As a temporary workaround, consider initializing hashes in vllm with a value that is no longer constant and predictable, or using a hashing algorithm that is less prone to collision, such as
sha256, although this may have an impact on performance and memory footprint. Avoid using prompts that are known to collide with other prompts in use until the issue is resolved.Exploit
Fix
Found an issue in the description? Have something to add? Feel free to write us 👾
Weakness Enumeration
Related Identifiers
Affected Products
Python
Vllm