Vulnerability in Vllm
CVE-2025-46570
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.
EPSS: 0.002 (16.1th percentile) — read the EPSS interpretation.
CVSS v3 metric
CVSS v3 base score 2.6 (Low). Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N.
Affected products
- Vllm
- Vllm-project Vllm — versions < 0.9.0
Weakness classification (CWE)
References
- security-advisories@github.com (x_refsource_CONFIRM, Vendor Advisory)
- security-advisories@github.com (x_refsource_MISC, Issue Tracking, Vendor Advisory)
- security-advisories@github.com (Patch, x_refsource_MISC)
Frequently asked questions
- What is CVE-2025-46570?
- CVE-2025-46570 is a low-severity vulnerability in Vllm, classified under CWE-208. CVSS score: 2.6/10. Published 2025-05-29.
- How severe is CVE-2025-46570?
- Low severity. CVSS v3 base score is 2.6 out of 10.