CVE-2025-48956
Last modified
CVE-2025-48956 is a high-severity vulnerability rated 7.5/10 on the CVSS scale. vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. EPSS estimates a 0.53% chance of exploitation in the next 30 days.
Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.
Metrics
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
Weakness Enumeration
Affected Software
| Vendor | Product | Versions |
|---|---|---|
| Vllm | Vllm | >= 0.1.0, < 0.10.1.1 |
References
Timeline
- Published
- Last Modified
- Status
- Analyzed
Frequently Asked Questions
What is CVE-2025-48956?
How severe is CVE-2025-48956?
How do I fix CVE-2025-48956?
Are you affected by CVE-2025-48956?
Run a free Strix scan to check your systems for this vulnerability.
Scan your code nowSource: NVD / NIST
