CVE-2026-105752

Katalog CVE

CVSS 3.1 · Low EPSS 0,22%

Kerentanan Exposure of Sensitive Information to an Unauthorized Actor pada vllm. Skor CVSS 3.1 3.1 (Low) menurut github.com.

Deskripsi (NVD)

vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/responses" requests rebuild the next-turn engine input without preserving the cache_salt value, placing the continuation prefix in the global unsalted cache namespace even when the caller enabled salting. On deployments with prefix caching enabled, which is the default, an authenticated tenant who can reconstruct a victim's low-entropy post-tool history can submit the same continuation and use the cached_tokens_per_turn count to determine whether the prefix was previously processed, defeating the intended tenant isolation of salted prefix caching. This issue is fixed in version 0.30.0.

Rincian

Terbit di NVD

5 Oktober 2026

Terakhir diubah

8 Oktober 2026

Status NVD

Analyzed

CVSS 3.1

3.1 (Low), sumber github.com
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N · uraikan di kalkulator

Jenis kelemahan (CWE)

CWE-200: Exposure of Sensitive Information to an Unauthorized Actor
CWE-524: Use of Cache Containing Sensitive Information

EPSS (30 hari)

0,22% peluang dieksploitasi; lebih tinggi dari 11,1% CVE lain

Produk dan versi terdampak

> Data dari konfigurasi CPE di NVD.

Referensi dan perbaikan

• https://github.com/vllm-project/vllm/security/advisories/GHSA-935w-9g4m-p28p mitigasi · advisory vendor
• https://github.com/vllm-project/vllm/commit/6a2a2bb02b563b83f946012959fd3927984d072a patch
• https://github.com/vllm-project/vllm/pull/50195 issue tracking · patch
• https://github.com/vllm-project/vllm/pull/51818 issue tracking · patch
• https://github.com/vllm-project/vllm/releases/tag/v0.30.0 release notes