🔐 CVE Alert

CVE-2026-96893

HIGH 7.3

Improper Neutralization of Input Used for LLM Prompting in GitLab

CVSS Score
7.3
EPSS Score
0.0%
EPSS Percentile
0th

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.

CWE CWE-1427
Vendor gitlab
Product gitlab
Ecosystems
Industries
Technology
Published Oct 13, 2026
Stay Ahead of the Next One

Get instant alerts for gitlab gitlab

Be the first to know when new high vulnerabilities affecting gitlab gitlab are published — delivered to Slack, Telegram or Discord.

Get Free Alerts → Free · No credit card · 60 sec setup

CVSS v3 Breakdown

CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
Required
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
None

Affected Versions

GitLab / GitLab
19.1 < 19.2.8 19.3 < 19.3.5 19.4 < 19.4.2

References

NVD ↗ CVE.org ↗ EPSS Data ↗
gitlab.com: https://gitlab.com/gitlab-org/gitlab/-/work_items/607968 docs.gitlab.com: https://docs.gitlab.com/releases/patches/patch-release-gitlab-19-4-2-released/

Credits

This vulnerability has been discovered internally by GitLab team member Mert Coskuner.