CVE-2026-112051: high-severity vulnerability in xorbitsai inference
Xinference through 4.0.1 Path Traversal via model_name in Custom Model Registration
Published · Updated
21Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 8.3epss 0.4%
exploitation probability
0.4%top 71% of all CVEs
observed exploitation
nono source reports it
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:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:N/VI:H/VA:L/SC:N/SI:N/SA:N
Affected products
xorbitsai · inferenceRelated CVEs — xorbitsai inference
In the same product, most dangerous first.
CVE-2026-61539CRITICALXinference: Remote code execution via unsafe `eval()` in Llama3 tool-call parsingEPSS 1.2%CVE-2026-76841HIGHXinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model LoadersEPSS 1.0%CVE-2026-85668HIGHXinference 3.3.0 Unauthenticated Arbitrary-Path File Read via /v1/models/llm/auto-registerEPSS 0.6%
References
https://github.com/xorbitsai/inference/blob/v4.0.1/xinference/model/cache_manager.py#L117-L134https://github.com/xorbitsai/inference/blob/v4.0.1/xinference/model/utils.py#L1175-L1182https://github.com/xorbitsai/inference/commit/beddc97ac211f8414597fe8479493be0603f7c84https://github.com/xorbitsai/inference/issues/5702https://www.vulncheck.com/advisories/xinference-through-4.0.1-path-traversal-via-model-name-in-custom-model-registration