vllm API endpoints vulnerable to Denial of Service Attacks
### 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.
beschreibt (1)
Zugehörige CVEs.
| ID | Schweregrad | ausnutzbar | ||
|---|---|---|---|---|
| CVE-2025-48956US | — | — | ||
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 singl… | ||||
Referenzen
Externe Belege — Patches, Meldungen, Analysen.
- https://github.com/advisories/GHSA-rxc4-3w6r-4v47ADVISORY
- https://github.com/vllm-project/vllmPACKAGE
- https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944WEB
- https://github.com/vllm-project/vllm/pull/23267WEB
- https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47WEB
- https://nvd.nist.gov/vuln/detail/CVE-2025-48956ADVISORY
- https://pypi.org/project/vllmPACKAGE
Advisories wie diese benennen die exponierten Produkte, die Angreifer auf Ihrer Angriffsfläche ins Visier nehmen. Sehen Sie mit einem kostenlosen Passiv-Scan, was exponiert ist.
Kostenloser Scan