High severity · published Oct 13, 2026
CVE-2026-96893
Improper Neutralization of Input Used for LLM Prompting in GitLab
7.3
CVSS
0.6%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Attack vector
Network
Complexity
Low
Privileges
Low
User interaction
Required
Confidentiality
High
Integrity
High
Availability
None
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.6% · higher than 48% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
GI
GitLab · GitLab
19.1 before 19.2.8; 19.3 before 19.3.5; 19.4 before 19.4.2 · source: vendor, NVD
Affected product
GI
GitLab
GitLab
More from GitLab
10.0
CVE-2026-85706
Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in GitLab
10.0
CVE-2021-22205
GitLab Community and Enterprise Editions Remote Code Execution Vulnerability
9.8
CVE-2023-7028
Weak Password Recovery Mechanism for Forgotten Password in GitLab
9.8
CVE-2021-22175
GitLab Server-Side Request Forgery (SSRF) Vulnerability
7.5
CVE-2021-39935
GitLab Community and Enterprise Editions Server-Side Request Forgery (SSRF) Vulnerability