Skip to content
Fencer Vulns
low 2.6

CVE-2025-25183 json

vLLM using built-in hash() from Python 3.12 leads to predictable hash collisions in vLLM prefix cache

published 2025-02-06 21 mo ago modified 2026-08-07 3 mo ago also EUVD-2025-4074 , GHSA-rm76-4mrf-v9r8 , PYSEC-2025-62

cvss
2.6
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.2%
EPSS 0.2% chance of exploitation in 30 days, percentile 8%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi vllm 0.7.2
  • vllm-project vllm 0.7.2
  • vllm vllm 0.7.2

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2025-25183 updated cvss 2.6

vllm: vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache

  • Red Hat Enterprise Linux AI (RHEL AI) bootc-intel-rhel9, bootc-nvidia-rhel9, bootc-azure-amd-rhel9, instructlab-amd-rhel9, bootc-aws-nvidia-rhel9, bootc-gcp-nvidia-rhel9, +4 more
    affected: workaround, no fix available “Using a hashing algorithm that is less prone to collision, such as sha256, for example, would be the best way to avoid the possibility of a collision.”

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
21 mo ago

Exploit prediction

0.19% chance of exploitation in the next 30 days, higher than 8% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 2.6 CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N
GitHub 3.1 2.6 CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N

Affected packages

ecosystem package affected fixed in
pypi vllm
<0.7.2
0.7.2

Affected products

  • vllm-project vllm

Classification

Weakness
  • CWE-354 Improper Validation of Integrity Check Value

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.