Use of cache containing sensitive information in vLLM - CVE-2026-105752
Published: November 9, 2026
Vulnerability details
The vulnerability allows an authenticated remote tenant to determine whether another tenant processed a guessed post-tool history in a shared vLLM deployment.
The vulnerability exists due to dropped cache_salt values during salted GPT-OSS Harmony tool continuations at /v1/responses, exposing continuation prefixes to the shared cache when prefix caching and operator-enabled tools are active. An authenticated remote tenant can submit a reconstructed history without a salt and inspect exact cached-token counts to identify matching victim activity.