Vulnerability in vllm-project vllm

[ Description ]Official 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.

[ Fixes ]Fixes and patches

No fix or interim patch is linked from our sources yet. Check the vendor references below and limit exposure of affected systems until a fix is available.

[ Advisories ]Government CERT advisories

• BSI CERT-Bund27 Sep 2026WID-SEC-2026-3604

  vllm: Multiple vulnerabilities Translated from German

  CVE-2026-109311CVE-2025-46570

[ References ]References

• github.com/vllm-project/vllm/security/advisories/GHSA-4qjh-9fv9-r85rx_refsource_CONFIRM
• github.com/vllm-project/vllm/pull/17045x_refsource_MISC
• github.com/vllm-project/vllm/commit/77073c77bc2006eb80ea6d5128f076f5e6c6f54fx_refsource_MISC