CVE-2026-96893
Improper Neutralization of Input Used for LLM Prompting in GitLab
Overview
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.
Source: OX vulnerability database
Severity
7.3 · HIGH
CVSS 3.1 base score, scored by NVD.
- Attack vector
- Network
- Attack complexity
- Low
- Privileges required
- Low
- User interaction
- Required
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- None
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Weakness: CWE-74
Affected packages · 1
| Ecosystem | Package | Vulnerable | Fixed in |
|---|---|---|---|
| Bitnami | gitlab | >=19.1.0, <19.2.8>=19.3.0, <19.3.5>=19.4.0, <19.4.2 | 19.2.819.3.519.4.2 |
Open a package to see all its vulnerabilities.
Operating systems · 3 fixes
minimos 1 release · 3 packages
| Release | Package | Fixed in |
|---|---|---|
| gitlab-rails-19-2 | 19.2.8-r0 | |
| gitlab-rails-19-3 | 19.3.5-r0 | |
| gitlab-rails-19-4 | 19.4.2-r0 |
References
OX Radar and Response Center
Find threats in your stack.
OX Radar can check high-priority threats, like critical package CVEs, against your context.
Each incident is marked Detected or Not Detected with a remediation plan and proof all tracked in the Response Center.