GitLab, as the CVE numbering authority, published CVE-2026-90970 on 2026-10-02: in the AI Gateway component, an authenticated user with Duo Agent Platform access could escape the prompt template sandbox through a specially crafted flow configuration and run arbitrary commands on the gateway. The CVE record rates it critical (CVSS 3.1 base score 9.9) and lists fixes in versions 19.2.4, 19.3.2 and 19.4.1. The record also carries a CISA assessment, added the same day, that lists exploitation as none; The Hacker News adds that only organizations hosting their own gateway need to act.
GitLab
Oct 2, 2026
GitLab discloses a critical AI Gateway flaw letting a Duo Agent Platform user run commands on self-hosted gateways (CVE-2026-90970)
May 22, 2025
Legit Security finds GitLab Duo prompt injection that could leak private source code
Legit Security reports that hidden instructions in merge requests, comments or code could steer GitLab Duo, combined with unsanitized HTML in streamed responses, to leak private project code and confidential issues. GitLab was notified on 2025-02-12 and patched rendering of external-domain HTML tags.