CVE-2025-25183: vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache
(updated )
Maliciously constructed prompts can lead to hash collisions, resulting in prefix cache reuse, which can interfere with subsequent responses and cause unintended behavior.
References
- github.com/advisories/GHSA-rm76-4mrf-v9r8
- github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7
- github.com/python/cpython/pull/99541
- github.com/vllm-project/vllm
- github.com/vllm-project/vllm/commit/73b35cca7f3745d07d439c197768b25d88b6ab7f
- github.com/vllm-project/vllm/pull/12621
- github.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8
- nvd.nist.gov/vuln/detail/CVE-2025-25183
Detect and mitigate CVE-2025-25183 with GitLab Dependency Scanning
Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →