Authenticated command execution via prompt-template sandbox escape
Published Oct 2, 2026 · Updated Oct 2, 2026
Template injection in GitLab AI Gateway allows remote authenticated users to execute commands via crafted Duo Agent Platform flows. A specially crafted flow configuration escapes the prompt template sandbox; GitLab has not published the exact parsing or bypass step. Exploitation requires authenticated Duo Agent Platform access, and command execution occurs on the AI Gateway.
Summary
What happened
Template injection in GitLab AI Gateway allows remote authenticated users to execute commands via crafted Duo Agent Platform flows. A specially crafted flow configuration escapes the prompt template sandbox; GitLab has not published the exact parsing or bypass step. Exploitation requires authenticated Duo Agent Platform access, and command execution occurs on the AI Gateway.
The record
- CVE
- CVE-2026-90970
- Published
- Oct 2, 2026
- Updated
- Oct 2, 2026
- Vendor
- GitLab
- Product
- GitLab AI Gateway
- Classifications
- CWE-1336, T1190
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Oct 2, 2026CVE publishedPublication date reported by the CVE source.
- Oct 2, 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=18.1.6 <19.2.4
- Affected versionversion=19.3 <19.3.2
- Affected versionversion=19.4 <19.4.1
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
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