CVE-2026-96893

Improper Neutralization of Input Used for LLM Prompting in GitLab

GitLab GitLabApplications & CMS

CVSS

7.3High

ExploitationNo known exploitationNot in CISA KEV, which does not prove it is unexploitedCISA KEV

Exploit odds (EPSS)0.53%Chance of exploitation activity in the next 30 days, higher than 44% of CVEs. Scored 23 Oct 2026FIRST EPSS

Fixed in19.2.8Also 19.3.5, 19.4.2CVE List

Published13 Oct 2026Updated 14 Oct 2026CVE List

What fixes it

19.2.8GitLabCVE List
19.3.5GitLabCVE List
19.4.2GitLabCVE List

A fixed version on one release line is not the upgrade target for every line. Check your exact version and any vendor backports.

Reports 1

1 outlet mention it. Reports are not confirmation; each links to its source.

GitLab Critical Patch Release: 19.4.2, 19.3.5, 19.2.8GitLab releases, 12 Oct 2026

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.

Text from CVE List

Affected versions 3

GitLabaffected: 19.1 before 19.2.8CVE List
GitLabaffected: 19.3 before 19.3.5CVE List
GitLabaffected: 19.4 before 19.4.2CVE List