CVE-2025-46570
Last modified
CVE-2025-46570 is a low-severity vulnerability rated 2.6/10 on the CVSS scale. 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). EPSS estimates a 0.25% chance of exploitation in the next 30 days.
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.
Metrics
CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:U/C:L/I:N/A:N
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | < 0.9.0 |
References
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2025-46570?
How severe is CVE-2025-46570?
How do I fix CVE-2025-46570?
Are you affected by CVE-2025-46570?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
