GitLab EE AI Agent Instruction Injection (19.1-19.2.8, 19.3-19.3.5, 19.4-19.4.2)
CVE-2026-96893 Published on October 13, 2026
Improper Neutralization of Input Used for LLM Prompting in GitLab
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.
Vulnerability Analysis
CVE-2026-96893 can be exploited with network access, requires user interaction and a small amount of user privileges. This vulnerability is considered to have a low attack complexity. The potential impact of an exploit of this vulnerability is considered to have a high impact on confidentiality and integrity, and no impact on availability.
Weakness Type
Products Associated with CVE-2026-96893
Want to know whenever a new CVE is published for GitLab? stack.watch will email you.
Affected Versions
GitLab:- Version 19.1 and below 19.2.8 is affected.
- Version 19.3 and below 19.3.5 is affected.
- Version 19.4 and below 19.4.2 is affected.