Public mode

No access to your tenant or devices. Every item links to its source. What this means

Sources need attention Customize Public modeDiscuss ChangeIntel on Discord

vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle

CVSS 3.1 3.1 LOWCheck source for fixed versionsKEV status unknown

Historical advisory recorded 23 Oct 2026 15:48:27 UTC. Read the latest advisory.

cve-program · CVE-2026-105752

Published

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.

Read the publisher's advisory

Affected versions, risk and source history

Related advisories and sources

This historical advisory does not include today's related changes. Open the latest advisory to find current connections.

ChangeIntel

An IT change radar: releases, security, known issues, retirements, documentation changes, and service status from public sources. Every item links to supporting evidence; dates and statuses can change after they are read.

Sources read 17 Nov 02:47 UTC · 274 of 275 readable · 250 fully read · 20 waiting for GitHub's hourly limit · documentation 469/469 current