CriticalVulnerability
CVE-2026-90970: GitLab AI Gateway prompt template sandbox escape via crafted flow configuration
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-90970
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 17.5%
Summary
GitLab fixed a vulnerability in its AI Gateway component, CVE-2026-90970, affecting versions from 18.1.6 before 19.2.4, 19.3 before 19.3.2, and 19.4 before 19.4.1. Under certain conditions, an authenticated user with Duo Agent Platform access could escape the prompt template sandbox through a specially crafted flow configuration and execute arbitrary commands on the AI Gateway.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Coverage
News, research and other items that mention CVE-2026-90970.
- GitLab Patches Critical 9.9 AI Gateway Flaw Allowing Command Execution on Self-Hosted ServersThe Hacker News · 2026-10-02
Related items
- MediumCVE-2026-130358: AdminNeo before 5.9.1 contains a missing authentication vulnerability in the ClaudeSqlPlugin, GeminiSqlPlugin, and…Same vendor · NVD/CVE Database
- MediumCVE-2026-111372: AI ChatBot for WooCommerce WoowBot plugin authorization bypass in RAG syncSame vendor · NVD/CVE Database
- HighCVE-2026-117560: ATXP Gemini CLI extension OS command injection in runAtxp() via MCP parametersSame vendor · NVD/CVE Database
- MediumCVE-2026-89278: GPTranslate WordPress plugin exposes plaintext API key to unauthenticated usersSame vendor · NVD/CVE Database
- CriticalCVE-2026-19407: Google Cloud Gemini Enterprise Agent Platform SDK for Python bucket squattingSame vendor · NVD/CVE Database