Description
GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user to inject specially crafted content into AI agent instructions, potentially causing unintended command execution attributed to other users, due to improper neutralization of special elements in AI conversation context construction.
Affected products
gitlab: gitlab
References2
- docs.gitlab.com/releases/patches/patch-release-gitlab-19-4-2-re… Release NotesVendor Advisory
- gitlab.com/gitlab-org/gitlab/-/work_items/607968 Issue Tracking
Metrics
- CVSS 3.1
-
7.3
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N - EPSS — exploit probability
- 1% percentile: 48 · as of 11 November 2026
- CWE
- CWE-74
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.