Use of Cache Containing Sensitive Information Affecting vllm package, versions [,0.30.0)
Threat Intelligence
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
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-PYTHON-VLLM-20574182
- published8 Oct 2026
- disclosed6 Oct 2026
- creditClinton Thomas, Lucas Bourtoule
Introduced: 6 Oct 2026
NewCVE-2026-105752 (opens in a new tab)How to fix?
Upgrade vllm to version 0.30.0 or higher.
Overview
vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs
Affected versions of this package are vulnerable to Use of Cache Containing Sensitive Information via the /v1/responses endpoint, where tokens_input stores the salt on the engine input only when it is passed, causing continuation inputs to land in an unsalted namespace. An authenticated attacker can exploit this namespace separation to tamper with response integrity, resulting in unauthorized modification of output data.