Authenticated command execution via AI-context injection
Published Oct 13, 2026 · Updated Oct 13, 2026
Prompt injection in GitLab EE AI agents allows remote authenticated users to cause command execution via crafted instructions. AI conversation context construction fails to neutralize special elements, allowing crafted content to enter agent instructions. Exploitation requires user interaction and produces unintended commands attributed to other users; the specific interaction and command environment are undisclosed.
Summary
What happened
Prompt injection in GitLab EE AI agents allows remote authenticated users to cause command execution via crafted instructions. AI conversation context construction fails to neutralize special elements, allowing crafted content to enter agent instructions. Exploitation requires user interaction and produces unintended commands attributed to other users; the specific interaction and command environment are undisclosed.
The record
- CVE
- CVE-2026-96893
- Published
- Oct 13, 2026
- Updated
- Oct 13, 2026
- Vendor
- GitLab
- Product
- GitLab
- Classifications
- Unavailable
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Oct 13, 2026CVE publishedPublication date reported by the CVE source.
- Oct 13, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=19.1 <19.2.8
- Affected versionversion=19.3 <19.3.5
- Affected versionversion=19.4 <19.4.2
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Activity data is delayed. The latest report is Sep 28, 2026.
Weakness, pattern, technique
No sourced classifications are available.
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Get started to see how Hinoki identifies affected software and validates exploitability in your environment.
Get started