# xorbitsai inference.

Every CVE that names xorbitsai inference among its affected products, newest first. Vendors and products are as the CNA wrote them.

## Records, newest first

- [Xinference through 4.0.1 Path Traversal via model_name in Custom Model Registration](https://agentprime.io/advisories/CVE-2026-112051.md)
  `CVE-2026-112051` · CVE record: xorbitsai inference · CVSS 8.3 High · Not analysed yet · Published 18 Oct 2026 · Tags: Path traversal
- [Xinference 3.3.0 Unauthenticated Arbitrary-Path File Read via /v1/models/llm/auto-register](https://agentprime.io/advisories/CVE-2026-85668.md)
  `CVE-2026-85668` · CVE record: xorbitsai inference · CVSS 8.7 High · Not analysed yet · Published 4 Sept 2026 · Tags: Path traversal
- [Xinference through 2.11.0 Remote Code Execution via Hardcoded trust_remote_code in Model Loaders](https://agentprime.io/advisories/CVE-2026-76841.md)
  `CVE-2026-76841` · CVE record: xorbitsai inference · CVSS 8.7 High · Not analysed yet · Published 24 Aug 2026 · Tags: Code injection

## Filters and formats

Filters are query parameters on this URL: `q` (words, as in a web search engine: `"a phrase"`, `OR`, `-word`; an id; a package or product name), `severity` (low, medium, high or critical), `critical=1`, `kev=1`, `ecosystem` (npm, pypi, packagist, go, maven, rubygems, crates, nuget, hex), `kind=package`, `assigner` (a CNA’s short name), `min_score` and `state`. Each record’s title links to its Markdown page.

- The same list as JSON: <https://api.agentprime.io/v1/advisories?technology=xorbitsai-inference>
- Every list: <https://agentprime.io/advisories.md>, critical: <https://agentprime.io/advisories/critical.md>; by weakness: <https://agentprime.io/advisories/tag/sql-injection.md> and the other tags in <https://agentprime.io/llms.txt>; by technology: `/advisories/technology/<slug>.md` (`fortinet-fortimail`)

---

The web page: <https://agentprime.io/advisories/technology/xorbitsai-inference/>. Everything for agents: <https://agentprime.io/llms.txt>.