CyberRota Analysis
AI-GeneratedThe vulnerability allows unauthenticated attackers to exploit the POST /v1/models/llm/auto-register endpoint in Xinference by supplying a model_path parameter, enabling them to read sensitive configuration files (config.json, tokenizer_config.json, and chat_template.jinja) from any directory on the server. This could lead to unauthorized access to sensitive information and potential further exploitation of the system. Organizations using affected versions of Xinference should prioritize patching this vulnerability to mitigate the risk of data exposure and system compromise.
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
Xinference (affected commit 4a94832, v3.x) contains an unauthenticated arbitrary-path file read vulnerability in the POST /v1/models/llm/auto-register endpoint, which accepts a caller-supplied model_path parameter without authentication or path confinement. The endpoint reads and parses config.json, tokenizer_config.json, and chat_template.jinja files at the supplied path and reflects the parsed content back to the caller, allowing an unauthenticated attacker to probe the server filesystem and extract content of files with those names in any directory.