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.

Xinference v3.x (affected commit 4a94832) contains an unauthenticated arbitrary-path file read vulnerability in the POST /v1/models/llm/auto-register endpoint. The endpoint accepts a caller-supplied model_path parameter without any authentication or path confinement checks. It reads and parses config.json, tokenizer_config.json, and chat_template.jinja files from the attacker-supplied path and reflects the parsed content back to the caller. This allows an unauthenticated attacker to probe the server filesystem and extract sensitive file contents from any directory. No credentials or privileges are required to exploit this vulnerability. The issue has been documented in GitHub issue #5176 and reported via VulnCheck advisories.