p PatchFirst

CVE-2025-48942

CVE-2025-48942 · vLLM DOS: Remotely kill vllm over http with invalid JSON schema

This page contains facts from public vulnerability sources. Check the original advisory before updating.

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.

CVSS 6.5 · Medium · EPSS 0.6% · Fix available

Published
Updated

Stack: python

Affected products and versions

  • vllm

    Versions
    • >= 0.8.0, < 0.9.0: Affected

    No fix published

  • vllm PyPI

    Versions
    • 0.8.0
    • 0.8.1
    • 0.8.2
    • 0.8.3
    • 0.8.4
    • 0.8.5
    • 0.8.5.post1
    Affected ranges
    • ECOSYSTEM: ≥ 0.8.0, < 0.9.0

    Update to 0.9.0

  • vllm PyPI

    Versions
    • 0.8.0
    • 0.8.1
    • 0.8.2
    • 0.8.3
    • 0.8.4
    • 0.8.5
    • 0.8.5.post1
    Affected ranges
    • GIT: < 08bf7840780980c7568c573c70a6a8db94fd45ff
    • ECOSYSTEM: ≥ 0.8.0, < 0.9.0

    Update to 0.9.0

Original sources

Check your server →