CyberRota Analysis
AI-GeneratedThe vLLM inference engine is vulnerable to information disclosure due to improper handling of FastAPI RequestValidationError objects, which can expose sensitive system details such as OS usernames, Python versions, and internal package structures through unauthenticated malformed JSON requests. This vulnerability affects versions prior to 0.26.0 and poses a medium risk, making it essential for organizations using vLLM for large language model serving to prioritize upgrading to the latest version to mitigate potential data leaks.
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 is an inference and serving engine for large language models. Prior to 0.26.0, the validation_exception_handler in vllm/entrypoints/openai/server_utils.py converts FastAPI RequestValidationError objects with str(exc), and sanitize_message in vllm/entrypoints/utils.py does not remove traceback-style file paths, allowing unauthenticated malformed JSON requests to /v1/chat/completions, /v1/completions, /tokenize, and /detokenize to disclose the OS username, home and virtual-environment paths, Python version, internal package structure, line numbers, and endpoint handler names. This issue is fixed in version 0.26.0.