Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-85668 – Unauthenticated Arbitrary File Read – Xinference (xorbitsai/inference) ≤3.3.0

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-85668 is an unauthenticated arbitrary-path file read vulnerability in Xinference (the xinference PyPI package by xorbitsai), an open-source distributed AI model inference framework. The flaw resides in the POST /v1/models/llm/auto-register API endpoint, which accepts a caller-supplied model_path without authentication or path confinement, allowing attackers to read configuration files from arbitrary locations on the host filesystem. The issue affects versions 0 through 3.3.0 and carries a severity score of 8.7 (HIGH).

Technical details

  • Root cause: The auto-register endpoint accepts an attacker-controlled model_path parameter and uses it to load and parse files without validating or confining the path to an approved directory.
  • Trigger conditions: An attacker sends a crafted POST request to /v1/models/llm/auto-register specifying a path to a location of interest on the target server; no prior authentication or user interaction is required.
  • Attack vector: Network — the endpoint is reachable over HTTP(S) without credentials (Attack Complexity: Low, Privileges Required: None, User Interaction: None).
  • Impact: The endpoint reads and parses config.json, tokenizer_config.json, and chat_template.jinja at the supplied path and reflects the parsed content back in the API response, letting an unauthenticated remote attacker probe the filesystem and extract the contents of files matching those names anywhere on the server.

Affected software

  • xorbitsai inference (PyPI package xinference), versions 0 through 3.3.0

Severity

  • CVSS score: 8.7 (HIGH)
  • CVSS v4.0 vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
  • CVSS v3.1 equivalent: 7.5 (HIGH), vector CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Mitigation and recommended actions

  • Immediate: No official patched release has been published by the maintainers as of this writing — the issue tracker entry for this vulnerability was closed by the project as "not planned." Security teams should not assume upgrading resolves this issue and should verify current project guidance before relying on a version bump alone.
  • Network mitigations: Restrict or disable public/unauthenticated access to the Xinference API, especially the /v1/models/llm/auto-register endpoint, by placing it behind an authenticating reverse proxy, VPN, or network ACLs limiting access to trusted hosts only.
  • Workarounds: Do not expose Xinference management/registration endpoints directly to the internet; monitor for unexpected requests to auto-register and audit for unauthorized file-read attempts; restrict filesystem permissions available to the Xinference process to limit the value of any successfully read files.

How IONIX identifies potentially affected assets

IONIX matches the following signals against data already collected when it crawled the asset; identifying the technology sends no request beyond that crawl.

  • Page title: Xinference

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge