Skip to content
OpenAdvisories

Vendor

vLLM

128 known vulnerabilities.

1 result · Clear filters · Feed

  • High 8.8
    CVE-2026-22807 Public exploit

    vLLM affected by RCE via auto_map dynamic module loading during model initialization

    vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attack…