Information Exposure Affecting vllm package, versions *


Severity

Recommended
low

Based on default assessment until relevant scores are available.

Threat Intelligence

EPSS
0.22% (12th percentile)

Do your applications use this vulnerable package?

In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.

Test your applications
  • Snyk IDSNYK-MINIMOSLATEST-VLLM-20542068
  • published7 Oct 2026
  • disclosed5 Oct 2026

Introduced: 5 Oct 2026

NewCVE-2026-105752  (opens in a new tab)
CWE-200  (opens in a new tab)
CWE-524  (opens in a new tab)

How to fix?

There is no fixed version for Minimos:latest vllm.

NVD Description

Note: Versions mentioned in the description apply only to the upstream vllm package and not the vllm package as distributed by Minimos. See How to fix? for Minimos:latest relevant fixed versions and status.

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.