Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
vLLM versions before 0.7.2 use Python's built-in hash() for prefix caching, and on Python 3.12 the hash of None is a predictable constant, making collisions easier to engineer. An attacker who can submit crafted prompts could cause cached content from one prompt to be reused for another, potentially affecting responses. Upgrade vLLM to 0.7.2 or later.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 2.6 | Low | 3.1 | CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0019, the 8th percentile, on 5 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:40 UTC First seen by agentprime
- 31 Oct 2026, 14:40 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-rm76-4mrf-v9r8
- OSV: GHSA-rm76-4mrf-v9r8
- github.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8
- nvd.nist.gov/vuln/detail/CVE-2025-25183
- github.com/python/cpython/pull/99541
- github.com/vllm-project/vllm/pull/12621
- github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7
- github.com/vllm-project/vllm/commit/73b35cca7f3745d07d439c197768b25d88b6ab7f
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-62.yaml
- github.com/vllm-project/vllm