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.
Announced
Evidence and details
Imported from structured advisory data. Source references identify upstream records or fields; verify affected versions and your deployed configuration.
Security context
Source reference: cve:CVE-2026-96893
GitLab
Source reference: /containers/cna/affected/0/product
- Affected versions
- Not stated in this record
- Fixed versions
- Not stated in this record
- Prerequisites
- Not stated in this record
- Related CVEs
- CVE-2026-96893
Source reference:
/cveMetadata/cveId
Publisher severity
high
Source reference: /containers/cna/metrics