CVE-2026-96893 Improper Neutralization of Input Used for LLM Prompting in GitLab
HighCVSS 7.3
EPSS 0.58%
- Published
- Updated
- Exploit status
- No public exploit known
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
| Product | Affected versions | Fixed in |
|---|---|---|
| gitlab | >= 19.1, < 19.2.8 | 19.2.8 |
| gitlab | >= 19.3, < 19.3.5 | 19.3.5 |
| gitlab | >= 19.4, < 19.4.2 | 19.4.2 |
| gitlab | >= 19.1.0, < 19.2.8 | 19.2.8 |
| gitlab | >= 19.3.0, < 19.3.5 | 19.3.5 |
| gitlab | >= 19.4.0, < 19.4.2 | 19.4.2 |
References
- gitlab.com issue-tracking
- GitLab Critical Patch Release: 19.4.2, 19.3.5, 19.2.8 release-notes vendor-advisory