p PatchFirst

CVE-2026-96893

CVE-2026-96893 · Improper Neutralization of Input Used for LLM Prompting in GitLab

This page contains facts from public vulnerability sources. Check the original advisory before updating.

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.

CVSS 7.3 · High · EPSS 0.6% · Fix available

Published
Updated

Stack: system

Affected products and versions

  • gitlab

    Versions
    • ≥ 19.1, < 19.2.8: Affected (semver)
    • ≥ 19.3, < 19.3.5: Affected (semver)
    • ≥ 19.4, < 19.4.2: Affected (semver)

    Update to 19.2.8; Update to 19.3.5; Update to 19.4.2

  • gitlab Ubuntu:16.04:LTS

    Versions
    • 8.4.3+dfsg-9
    • 8.4.3+dfsg-12
    • 8.5.8+dfsg-5
    Affected ranges
    • ECOSYSTEM: (−∞, +∞)

    No fix published

Original sources

Check your server →