Skip to content
CSA Labs Research·Indexed by this site · Originally publishedSelectedAttention44

Xinference Actor Layer RCE Vulnerability: Self-Hosted Inference Becomes an Initial Intrusion Entry Point

Xinference Actor-Layer RCE: Self-Hosted Inference as Initial Access

AI summary

Xorbits Xoscar, the underlying layer of the Xinference model serving platform, has an unauthenticated remote code execution vulnerability, CVE-2026-49950 (CVSS v4.0 score 9.3), affecting all versions from 0.1.0 to 0.11.2. These versions pass actor pool inbound traffic to cloudpickle.loads() for deserialization before authenticating the sender, so an attacker who can connect to the actor pool port can execute code; researcher Valentin Lobstein says the process often runs as root on GPU nodes, and exploitation can obtain a root shell in memory without leaving files on disk. In distributed mode, the supervisor and worker pools bind to 0.0.0.0 by default, and authentication on the REST API at port 9997 does not cover the actor port; a public exploit module exists, and as of October 22 there were no reports of in-the-wild exploitation.

Why it was selected

Authentication is off by default in the fixed version, and Xinference clusters that are only upgraded without configuring XOSCAR_AUTH_KEY remain exploitable.

Read originallabs.cloudsecurityalliance.org