# Red Hat AI Inference Server.

Every CVE that names Red Hat AI Inference Server among its affected products, newest first. Vendors and products are as the CNA wrote them.

## Records, newest first

- [Data-sciences-pipeline: dsp: v1 argo template path accepts arbitrary workflow spec, bypassing all v2 security hardening](https://agentprime.io/advisories/CVE-2026-18621.md)
  `CVE-2026-18621` · CVE record: Red Hat Red Hat OpenShift AI 2.25 and 3 more · CVSS 7.6 High · Not analysed yet · Published 10 Aug 2026 · Tags: Privilege escalation
- [Libaom: libaom: remote code execution via svc layer context handling with attacker-controlled frames](https://agentprime.io/advisories/CVE-2026-56211.md)
  `CVE-2026-56211` · CVE record: Red Hat Red Hat Enterprise Linux AI 3.3 for RHEL 9 and 4 more · CVSS 7.1 High · Not analysed yet · Published 19 Jun 2026 · Tags: Memory corruption
- [Libaom: libaom: heap-buffer-overflow read via missing bounds check in ctrl_set_layer_id](https://agentprime.io/advisories/CVE-2026-56210.md)
  `CVE-2026-56210` · CVE record: Red Hat Red Hat Enterprise Linux AI 3.3 for RHEL 9 and 4 more · CVSS 7.1 High · Not analysed yet · Published 19 Jun 2026 · Tags: Memory corruption
- [Libaom: libaom: arbitrary address write via svc layer context oob and cyclic refresh map pointer hijack](https://agentprime.io/advisories/CVE-2026-56209.md)
  `CVE-2026-56209` · CVE record: Red Hat Red Hat Enterprise Linux AI 3.3 for RHEL 9 and 4 more · CVSS 7.1 High · Not analysed yet · Published 19 Jun 2026 · Tags: Memory corruption
- [Ffmpeg: ffmpeg: denial of service and potential arbitrary code execution via signed integer overflow in dvd subtitle parser](https://agentprime.io/advisories/CVE-2026-6385.md)
  `CVE-2026-6385` · CVE record: Red Hat Lightspeed Core and 3 more · CVSS 6.5 Medium · Not analysed yet · Published 15 Apr 2026 · Tags: Memory corruption
- [Ai-inference-server: authentication bypass via unprotected inference endpoint in api](https://agentprime.io/advisories/CVE-2025-6920.md)
  `CVE-2025-6920` · CVE record: Red Hat Red Hat AI Inference Server · CVSS 5.3 Medium · Not analysed yet · Published 1 Jul 2025 · Tags: Authentication bypass

## 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=red-hat-ai-inference-server>
- 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/red-hat-ai-inference-server/>. Everything for agents: <https://agentprime.io/llms.txt>.