Skip to content
CVE PROGRAM SOURCE RECORD7.3 High

CVE-2026-96893

Improper Neutralization of Input Used for LLM Prompting in GitLab

Read JSON ↗CVE.org ↗
Status
Published
Published
Updated
Assigning organization
GitLab

Description

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.

Affected products

Version statuses are supplied by the assigning organization. Consult the original record for detailed ranges and platform conditions.

GitLab GitLab

Default version status: unaffected

  • 19.1 to < 19.2.8affected
  • 19.3 to < 19.3.5affected
  • 19.4 to < 19.4.2affected

References