CVE-2026-90970
9.9 CRITICALPublished 2026-10-02 · Updated 2026-10-02
AI risk analysis
- Summary
- This vulnerability allows an authenticated user with Duo Agent Platform access to escape the prompt template sandbox, leading to potential arbitrary command execution on the AI Gateway.
- Exploitability
- Exploitation requires an authenticated user with specific access and a specially crafted flow configuration, making it moderately difficult to exploit.
- Blast radius
- If exploited, this could result in significant damage, including unauthorized command execution on the AI Gateway.
- Detection
- No reliable host or network indicator is derivable from the published description.
- Prioritized remediation
- Upgrade to GitLab AI Gateway 19.3.2 or later.
Analysis generated locally by qwen2.5:7b-instruct (no data left the box). AI-assisted — verify against primary sources before acting.
NVD description
GitLab has remediated a vulnerability in the GitLab AI Gateway component affecting all versions of the AI Gateway from 18.1.6 before 19.2.4, 19.3 before 19.3.2, and 19.4 before 19.4.1 that, under certain conditions, could have allowed an authenticated user with Duo Agent Platform access to escape the prompt template sandbox via a specially crafted flow configuration, resulting in arbitrary command execution on the AI Gateway.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
Weaknesses
CWE-1336
All references
Source data: NVD (nvd.nist.gov), public domain. Exploit-DB.ai adds local AI analysis for defensive use only.
Related CVEs
- HIGHCVE-2026-105985PoC
- HIGHCVE-2026-88064PoC
- HIGHCVE-2026-94109PoC
- CRITICALCVE-2026-97359PoC
- HIGHCVE-2022-51019PoC
- HIGHCVE-2025-51457
- CRITICALCVE-2025-66455PoC
- HIGHCVE-2026-100254
Related by shared AI tags and CWE weakness class. Browse the full archive.