Uncaught Exception The advisory has been revoked - it doesn't affect any version of package py3.10-vllm-cuda-12.6  (opens in a new tab)


Threat Intelligence

EPSS
0.58% (48th 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-CHAINGUARDLATEST-PY310VLLMCUDA126-14889384
  • published7 Jan 2026
  • disclosed30 May 2025

Introduced: 30 May 2025

CVE-2025-48942  (opens in a new tab)
CWE-248  (opens in a new tab)

Amendment

The Chainguard security team deemed this advisory irrelevant for Chainguard:latest.

NVD Description

Note: Versions mentioned in the description apply only to the upstream py3.10-vllm-cuda-12.6 package and not the py3.10-vllm-cuda-12.6 package as distributed by Chainguard.

vLLM is an inference and serving engine for large language models (LLMs). In versions 0.8.0 up to but excluding 0.9.0, hitting the /v1/completions API with a invalid json_schema as a Guided Param kills the vllm server. This vulnerability is similar GHSA-9hcf-v7m4-6m2j/CVE-2025-48943, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.