CVE-2025-46570
LOWDescription
vLLM is an inference and serving engine for large language models (LLMs). Prior to version 0.9.0, when a new prompt is processed, if the PageAttention mechanism finds a matching prefix chunk, the prefill process speeds up, which is reflected in the TTFT (Time to First Token). These timing differences caused by matching chunks are significant enough to be recognized and exploited. This issue has been patched in version 0.9.0.
How to fix
Remediation is compiled from vendor and distribution security advisories. Always confirm against the linked source for your exact version and platform.
CVSS v3 Vector
Exploitability
Impact
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N
Exploit Intelligence
Low risk: more likely to be exploited than 16% of all known CVEs.
References
Related Vulnerabilities
Other CWE-208 vulnerabilities, ordered by exploit likelihood. View all
| CVE | Severity | CVSS | EPSS | Exploited | Fix |
|---|---|---|---|---|---|
| CVE-2019-9494 | Medium | 5.9 | 3.7% | - | Fix |
| CVE-2019-16782 | Medium | 6.3 | 3.7% | - | Fix |
| CVE-2025-53940 | Unscored | - | 2.6% | - | - |
| CVE-2020-1926 | Medium | 5.9 | 2.5% | - | Fix |
| CVE-2021-43298 | Critical | 9.8 | 2.3% | - | Fix |
| CVE-2024-29995 | High | 8.1 | 1.5% | - | Fix |
Embed a live status badge for CVE-2025-46570
Markdown
[](https://tridentstack.com/cve/CVE-2025-46570)HTML
<a href="https://tridentstack.com/cve/CVE-2025-46570"><img src="https://tridentstack.com/cve/badge/CVE-2025-46570.svg" alt="CVE-2025-46570"></a>Find and fix vulnerabilities across your fleet
TridentStack Control continuously scans your Windows, macOS, and Linux fleet for known vulnerabilities, prioritizes them by severity and active exploitation, and patches them automatically.
Start freeThis product uses NVD data but is not endorsed or certified by the NVD. EPSS scores courtesy of FIRST.org (https://www.first.org/epss). Source: CISA KEV Catalog. Data as of 2025-06-24.