CVE-2026-15077 Improper Neutralization of Input Used for LLM Prompting in GitLab
Authenticated users can access unauthorized project data via AI-assisted code review due to improper input neutralization in GitLab EE.
- Exploited in the wild
- Not known
- Login needed
- Any signed-in user
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-15077?
CVE-2026-15077 is a medium-severity vulnerability in Gitlab Gitlab, published on 29 Jul 2026. Any signed-in user can exploit it over the network, with no action from the victim.
Official description
GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.1.3 and 19.2 before 19.2.1 that under certain conditions could have allowed an authenticated user to access information from unauthorized projects due to improper neutralization of untrusted content processed by the AI-assisted code review functionality.
Which versions are affected by CVE-2026-15077?
1 open source package ship an affected version, including gitlab. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
gitlab Bitnami | From 19.1.0 | 19.1.3, 19.2.1 |
Products include Gitlab Gitlab.
How do I fix CVE-2026-15077?
Upgrade gitlab to a fixed version for your release line: 19.1.3 or 19.2.1.
Is CVE-2026-15077 being exploited?
There is no known exploitation of CVE-2026-15077 in the wild and no public exploit code.
Other vulnerabilities in Gitlab Gitlab
- CVE-2026-97229 GitLab Community Edition and Enterprise Edition Integer Overflow or Wraparound
- CVE-2026-85706 GitLab Community Edition and Enterprise Edition Path Traversal
- CVE-2023-7028 GitLab Community and Enterprise Editions Improper Access Control
- CVE-2021-22205 GitLab Community and Enterprise Editions Remote Code Execution
- CVE-2021-39935 GitLab Community and Enterprise Editions Server-Side Request Forgery (SSRF)
Sources
Also known as BIT-gitlab-2026-15077, GHSA-349h-ggfr-h55v, MINI-fh5h-4jvj-xc2x, MINI-p52m-94x5-f3jv.