inference vulnerabilities

3 known vulnerabilities in inference from Xorbitsai. 3 are rated high or critical. Each entry lists the affected versions and the release that fixes it, where the vendor has published one.

Latest first

• 7.5 High severity

  inference: External Control of File Name or Path

  CVE-2026-85668Sep 4, 2026Xorbitsai

  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. Th

• 8.8 High severity

  inference: Improper Control of Generation of Code

  CVE-2026-76841Aug 24, 2026XorbitsaiEPSS 1.03%

  Xinference loads models with Hugging Face remote code execution unconditionally enabled, and before version 2.12.0 exposes no setting to disable it. Six loader call sites pass trust_remote_code=True as a literal or as an unconditional default: RerankModel._get

• 10.0 Critical severity

  inference: Improper Neutralization of Directives in Dynamically Evaluated Code

  CVE-2026-61539Aug 21, 2026XorbitsaiEPSS 1.23%

  Xinference is an inference API for running open-source, speech, and multimodal models. In 2.5.0 and earlier, Xinference passes attacker-influenced Llama3 tool-call output to eval() in xinference/model/llm/tool_parsers/llama3_tool_parser.py and xinference/model