Unauthenticated file disclosure via unconstrained model path
Published Sep 4, 2026 · Updated Sep 4, 2026
Path traversal in XorbitsAI Xinference 3.3.0 and earlier allows remote attackers to read selected server files through the auto-register API. The POST /v1/models/llm/auto-register endpoint passes model_path to _resolve_config_and_dir(), which joins it to fixed configuration filenames without path confinement and reflects parsed values. The API is unauthenticated by default; exposure permits probing and partial disclosure of config.json, tokenizer_config.json, and chat_template.jinja, not arbitrary byte-for-byte file reads.
Summary
What happened
Path traversal in XorbitsAI Xinference 3.3.0 and earlier allows remote attackers to read selected server files through the auto-register API. The POST /v1/models/llm/auto-register endpoint passes model_path to _resolve_config_and_dir(), which joins it to fixed configuration filenames without path confinement and reflects parsed values. The API is unauthenticated by default; exposure permits probing and partial disclosure of config.json, tokenizer_config.json, and chat_template.jinja, not arbitrary byte-for-byte file reads.
The record
- CVE
- CVE-2026-85668
- Published
- Sep 4, 2026
- Updated
- Sep 4, 2026
- Vendor
- XorbitsAI
- Product
- Xinference
- Classifications
- CWE-73, T1005
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 4, 2026CVE publishedPublication date reported by the CVE source.
- Sep 4, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <=3.3.0
What conditions does exploitation require?
What is affected?
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Public exploit references
- Xinference auto-register file-read proof of conceptproof of concept · validated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo