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.
Published: 2026-10-13
Score: 7.3 High
EPSS: n/a
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

Vendor Solution

Upgrade to versions 19.2.8, 19.3.5, 19.4.2 or above.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Tue, 13 Oct 2026 01:30:00 +0000

Type Values Removed Values Added
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.
Title Improper Neutralization of Input Used for LLM Prompting in GitLab
First Time appeared Gitlab
Gitlab gitlab
Weaknesses CWE-1427
CPEs cpe:2.3:a:gitlab:gitlab:*:*:*:*:*:*:*:*
Vendors & Products Gitlab
Gitlab gitlab
References
Metrics cvssV3_1

{'score': 7.3, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N'}


cve-icon MITRE

Status: PUBLISHED

Assigner: GitLab

Published:

Updated: 2026-10-13T01:05:41.162Z

Reserved: 2026-09-23T19:34:35.812Z

Link: CVE-2026-96893

cve-icon Vulnrichment

No data.

cve-icon NVD

Status : Received

Published: 2026-10-13T02:17:00.720

Modified: 2026-10-13T02:17:00.720

Link: CVE-2026-96893

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

No data.

Weaknesses
  • CWE-1427

    Improper Neutralization of Input Used for LLM Prompting