Skip to content
Patch Next
Sign inAdd to your agent

← Actionable
Low, CVSS 2.6amended

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

CVE-2025-25183GHSA-rm76-4mrf-v9r8

What to do

Vendor fix available. Upgrade each affected package to the fixed version on its release line (vllm 0.7.2), redeploy, then verify what is actually installed.

This page has no inventory attached, so it cannot say whether you are affected. A vendor fix is not proof that your deployment is fixed.

Add to your agent

Affected packages

  • PyPI vllm

    Affected
    < 0.7.2
    Fixed in
    0.7.2

Sources

Severity and exploitation
Exploitation
No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.
CVSS
2.6 · CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N
EPSS
  • CVE-2025-25183: 0.19% estimated exploitation activity in the next 30 days; percentile 8.80 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.
Source description

As published by the source; long descriptions are shortened.

Summary Maliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior. Details vLLM's 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. Impact 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. Solution We address this problem by initializing hashes in vllm with a value that is no longer constant and predictable. It will be different each time vllm runs. This restores behavior we got in Python versions prior to 3.12. Using a hashing algorithm that is less prone to collision (like sha256,…

Dates and revisions
Published by the source
Last modified by the source
Source last checked
  1. Revision 2 · amended ·

    Amended from ghsa record GHSA-rm76-4mrf-v9r8

  2. Revision 1 · created ·

    Published from osv record GHSA-rm76-4mrf-v9r8

Agent brief

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2025-25183

Advisory: vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
IDs: CVE-2025-25183, GHSA-rm76-4mrf-v9r8
Record: https://patchnext.com/advisories/cve-2025-25183 (revision 2, source checked 26 Oct 2026, 13:32 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Low (CVSS 2.6)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: vllm 0.7.2. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI vllm: affected < 0.7.2; fixed in 0.7.2

## Suggested inspection (read-only)
- `python -m pip show vllm`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on vllm.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-rm76-4mrf-v9r8 (OSV record GHSA-rm76-4mrf-v9r8 lists affected ranges: PyPI vllm >=0 <0.7.2 (fixed))
- Verified: https://github.com/advisories/GHSA-rm76-4mrf-v9r8 (GitHub-reviewed advisory GHSA-rm76-4mrf-v9r8 lists affected ranges: PyPI vllm >=0 <0.7.2)

Commands are suggestions: review each one before running it.

Loading voting…