CVE-2025-48956
highpriority · track · 0EPSS 0.006 · 47 %ileEURUUSEPSS · scored 2026-10-27
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.
cvss
Technical severity, 0–10. One row per scoring source.
base score 0–10 · higher = more severe · hover a vector to decode⚠ sources disagree · medium–high · 6.9–7.5
ssvc
A stakeholder decision — act, attend, or track — from exploitation and impact.
weaknesses
The CWE weakness classes this flaw belongs to.
affected products (4)
Products and version ranges known to be affected.
advisories (2)
Vendor and ecosystem advisories describing this.
- GHSA-rxc4-3w6r-4v47vllm API endpoints vulnerable to Denial of Service Attacks2025-08-21ghsa · osvUS
### Summary 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. ### Details The vulnerability leverages the abuse of HTTP headers. By setting a header such as `X-Forwarded-For` to a very large value like `("A" * 5_800_000_000)`, the server's HTTP parser or application logic may attempt to load the entire request into memory, overwhelming system resources. ### Impact _What kind of vulnerability is it? Who is impacted?_ Type of vulnerability: Denial of Service (DoS) ### Resolution Upgrade to a version of vLLM that includes appropriate HTTP limits by deafult, or use a proxy in front of vLLM which provides protection against this issue.
- PYSEC-2026-2021vllm API endpoints vulnerable to Denial of Service Attacks2026-07-07vendor · osvUS
### Summary 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. ### Details The vulnerability leverages the abuse of HTTP headers. By setting a header such as `X-Forwarded-For` to a very large value like `("A" * 5_800_000_000)`, the server's HTTP parser or application logic may attempt to load the entire request into memory, overwhelming system resources. ### Impact _What kind of vulnerability is it? Who is impacted?_ Type of vulnerability: Denial of Service (DoS) ### Resolution Upgrade to a version of vLLM that includes appropriate HTTP limits by deafult, or use a proxy in front of vLLM which provides protection against this issue.
also known as (7)
Other names and identifiers for this entity.
sources
Which sources assert this record, and when.
references (12)
External citations — patches, advisories, analysis.
- https://access.redhat.com/security/cve/cve-2025-48956cnnvd
- https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944cnnvd
- https://github.com/vllm-project/vllm/pull/23267cnnvd
- https://github.com/vllm-project/vllm/releasesPatchcnnvd
- https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47cnnvd
- https://nvd.nist.gov/vuln/detail/CVE-2025-48956cnnvd
- https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944enisa_euvd
- https://github.com/vllm-project/vllm/pull/23267enisa_euvd
Attackers weaponise vulnerabilities like this against internet-exposed services. See what is exposed on your perimeter with a free passive scan.
Free scan