Answer in brief
CVE-2026-105752 records a Low severity (CVSS 3.1) vulnerability in vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle. The current sources do not mark it as known exploited. The current feed maps vllm-project/vllm (generic), vllm (pip). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 3.1. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps vllm-project/vllm (generic), vllm (pip). Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| vllm-project/vllmgeneric | <0.30.0 | 0.30.0 |
| vllmpip | <0.30.0 | 0.30.0 |
Published upstream
Oct 5, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Oct 6, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Oct 5, 2026
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.
Quoted source text, attributed separately from HOL analysis.