Authorization Bypass Through User-Controlled Key Affecting vllm-openai-cuda-13.0 package, versions <0.31.0-r0
Threat Intelligence
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-CHAINGUARDLATEST-VLLMOPENAICUDA130-21175632
- published17 Oct 2026
- disclosed5 Oct 2026
Introduced: 5 Oct 2026
NewCVE-2026-105755 (opens in a new tab)How to fix?
Upgrade Chainguard vllm-openai-cuda-13.0 to version 0.31.0-r0 or higher.
NVD Description
Note: Versions mentioned in the description apply only to the upstream vllm-openai-cuda-13.0 package and not the vllm-openai-cuda-13.0 package as distributed by Chainguard.
See How to fix? for Chainguard 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.