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

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.

Source published

5 Oct 2026 22:32:59 UTC

Source modified

6 Oct 2026 14:48:10 UTC

Observed here

23 Oct 2026 15:48:27 UTC

Source terms

CVE Program Terms of Use

Original source record · Cite this exact observation · Complete original publisher JSON

This view projects the publisher's source fields for reading; the original JSON retains additional fields and CVE enrichment containers. Attribution: cve-program · CVE Program Terms of Use. Source text is retained; field grouping and change labels are provided by ChangeIntel.

CVSS 3.1 · 3.1 CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N