Authorization Bypass Through User-Controlled Key Affecting vllm-cu130 package, versions <0.30.0-r0


Severity

Recommended
low

Based on default assessment until relevant scores are available.

Threat Intelligence

EPSS
0.2% (10th 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-VLLMCU130-20542479
  • published7 Oct 2026
  • disclosed5 Oct 2026

Introduced: 5 Oct 2026

NewCVE-2026-105755  (opens in a new tab)
CWE-639  (opens in a new tab)

How to fix?

Upgrade Minimos:latest vllm-cu130 to version 0.30.0-r0 or higher.

NVD Description

Note: Versions mentioned in the description apply only to the upstream vllm-cu130 package and not the vllm-cu130 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, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0.