CyberRota Analysis
AI-GeneratedvLLM versions prior to 0.28.0 are vulnerable to a remote code execution flaw in the LlavaOnevision2 processor loader, which improperly handles the trust_remote_code parameter, allowing attackers to execute arbitrary code. This vulnerability poses a significant risk as it enables the execution of malicious models with elevated privileges, potentially compromising the integrity of the vLLM process. Organizations using vLLM should prioritize patching to version 0.28.0 or later to mitigate this high-severity threat.
Public Exploit Signal
A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.
Note: these links are listed for security research and verification purposes only.
Original NVD Description
vLLM before 0.28.0 contains a remote code execution vulnerability in the LlavaOnevision2 processor loader that ignores the trust_remote_code parameter when loading remote processor classes. Attackers can craft a malicious model with arbitrary code in processing_llava_onevision2.py that executes with vLLM process authority even when trust_remote_code is set to False.