CVE-2026-112051
6.5 MEDIUMpublic exploit availablePublished 2026-10-18 · Updated 2026-10-18
AI analysis for this CVE has not been generated yet. Raw NVD data is shown below.
NVD description
Xinference through 4.0.1 contains a path traversal vulnerability on Windows that allows unauthenticated attackers to write and delete arbitrary .json files via backslash sequences in model_name. Attackers can register a persisted custom model through POST /v1/model_registrations/{model_type} with names like ..\..\evil to overwrite configuration or data files writable by the Xinference process.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:H/A:L
Weaknesses
CWE-22
Public exploit & PoC references
- https://github.com/xorbitsai/inference/blob/v4.0.1/xinference/model/cache_manager.py#L117-L134
- https://github.com/xorbitsai/inference/blob/v4.0.1/xinference/model/utils.py#L1175-L1182
- https://github.com/xorbitsai/inference/commit/beddc97ac211f8414597fe8479493be0603f7c84
- https://github.com/xorbitsai/inference/issues/5702
All references
- https://github.com/xorbitsai/inference/blob/v4.0.1/xinference/model/cache_manager.py#L117-L134
- https://github.com/xorbitsai/inference/blob/v4.0.1/xinference/model/utils.py#L1175-L1182
- https://github.com/xorbitsai/inference/commit/beddc97ac211f8414597fe8479493be0603f7c84
- https://github.com/xorbitsai/inference/issues/5702
- https://www.vulncheck.com/advisories/xinference-through-4.0.1-path-traversal-via-model-name-in-custom-model-registration
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- HIGHCVE-2014-125130PoC
- HIGHCVE-2017-20284
- HIGHCVE-2021-48011PoC
- HIGHCVE-2023-54403PoC
- MEDIUMCVE-2024-58386PoC
- HIGHCVE-2024-58387PoC
- HIGHCVE-2024-58388PoC
- MEDIUMCVE-2025-1280
Related by shared AI tags and CWE weakness class. Browse the full archive.