CVE-2025-46570
LOW EPSS 16.1%
Published May 29, 20251y ago · Modified Jun 17, 20261w ago
2.6 CVSS 3.1
Published May 29, 2025 1y ago
Last Modified Jun 17, 2026 1w ago
Description
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.
CVSS Details
Base Score
Exploitability
Impact
Vector string
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N Attack Vector Network
Attack Complexity High
Privileges Required Low
User Interaction Required
Scope Unchanged
Confidentiality Low
Integrity None
Availability None
Threat Intelligence
EPSS Exploit Probability
16.1% percentile
Exploit & Patch Status
No Known Exploit
Patch Available
Weaknesses 2
CWE-203
CWE-208
Affected Products 1
| Vendor | Product | Version | Range |
|---|---|---|---|
| vllm | vllm | * | <0.9.0 |
References 3
- github.com https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f
- github.com https://github.com/vllm-project/vllm/pull/17045
- github.com https://github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85r
Remediation
- github.com https://github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54f