CVE-2026-90970 Improper Neutralization of Special Elements Used in a Template Engine in GitLab AI Gateway
Authenticated users with Duo Agent Platform access can execute arbitrary commands on the GitLab AI Gateway by escaping the prompt template sandbox.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-90970?
CVE-2026-90970 is a critical code injection vulnerability in GitLab AI Gateway, published on 2 Oct 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.1.6 before 19.2.4, 19.3 before 19.3.2, and 19.4 before 19.4.1 that, under certain conditions, could have allowed an authenticated user with Duo Agent Platform access to escape the prompt template sandbox via a specially crafted flow configuration, resulting in arbitrary command execution on the AI Gateway.
Weakness: CWE-1336
Which versions are affected by CVE-2026-90970?
How do I fix CVE-2026-90970?
No fix has been published for CVE-2026-90970 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-90970 being exploited?
There is no known exploitation of CVE-2026-90970 in the wild and no public exploit code.
Public exploit code: 1 proofs of concept on GitHub.
Sources
Also known as GHSA-5295-vp56-jghq.