Skip to content
CVE Tracker
  • Newest CVEsPage
  • Recently added to KEVPage
  • Rising exploitation (EPSS)Page
  • Weekly digestPage
  • StatisticsPage
  • WatchlistPage
  • API documentationPage
  • MCP serverPage
  • Data sourcesPage
  • ChangelogPage
  • AboutPage
  • How it's builtPage
Back

CVE-2026-96893

Improper Neutralization of Input Used for LLM Prompting in GitLab

High7.3EPSS 0.58%
Published
Updated
Reserved
Assigned by
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.

Scores

CVSS scores of CVE-2026-96893, by who scored it
Scored byCVSSScoreVector
GitLabCNA (assigner)3.1High7.3CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
NVDNVD · Analyzed3.1High7.3CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
EPSS (exploitation in 30 days)
0.58% · top 52% of all CVEs (6 Nov 2026)
CISA SSVC
Exploitation: none · Automatable: no · Technical impact: total
Loading the EPSS history…

The list uses the assigner's score when there is one, then CISA's, then NVD's: High 7.3.

Weakness

Affected products

  • GitLab · GitLab

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

What to do

Solution: Upgrade to versions 19.2.8, 19.3.5, 19.4.2 or above.

References (2)

Sources

The same CVE in the primary databases and aggregators, to check against.

Badge for a README or a ticket

CVE-2026-96893 badge
[![CVE-2026-96893](https://trackcve.app/badge/CVE-2026-96893.svg)](https://trackcve.app/cve/CVE-2026-96893)

Record last updated .