{"cve":"CVE-2025-25183","nvd":{"published":"2025-02-07T20:15:34.083","modified":"2026-06-17T09:00:26.433","status":"Analyzed","description":"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.","cvss_v4":null,"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:N/I:L/A:N","score":2.6},"cwes":["CWE-354"],"references":["https://github.com/python/cpython/commit/432117cd1f59c76d97da2eaff55a7d758301dbc7","https://github.com/vllm-project/vllm/pull/12621","https://github.com/vllm-project/vllm/security/advisories/GHSA-rm76-4mrf-v9r8"],"products":["vllm:vllm"],"source":"nvd","synced_at":"2026-10-19T21:59:18.731010617+00:00"},"epss":{"cve":"CVE-2025-25183","score":0.00191,"percentile":0.08767,"date":"2026-10-31"},"kev":null,"osv":[{"id":"GHSA-rm76-4mrf-v9r8","url":"https://osv.dev/vulnerability/GHSA-rm76-4mrf-v9r8","summary":"vLLM uses Python 3.12 built-in hash() which leads to predictable hash collisions in prefix cache","modified":"2026-08-07T08:12:27.666244627Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":["<0.7.2"],"fixed":["0.7.2"]}]},{"id":"PYSEC-2025-62","url":"https://osv.dev/vulnerability/PYSEC-2025-62","summary":"","modified":"2025-07-01T23:59:49.926776Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":["<0.7.2"],"fixed":["0.7.2"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}