Description
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.
Affected products
vllm: vllm
References5
- github.com/vllm-project/vllm/security/advisories/GHSA-935w-9g4m… MitigationVendor Advisory
- github.com/vllm-project/vllm/commit/6a2a2bb02b563b83f946012959f… Patch
- github.com/vllm-project/vllm/pull/50195 Issue TrackingPatch
- github.com/vllm-project/vllm/pull/51818 Issue TrackingPatch
- github.com/vllm-project/vllm/releases/tag/v0.30.0 Release Notes
Metrics
- CVSS 3.1
-
3.1
LOW
Score source: CNA
CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N - EPSS — exploit probability
- 0% percentile: 12 · as of 10 November 2026
- CWE
- CWE-200CWE-524
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.