CVE-2026-96893: high-severity vulnerability in GitLab
Improper Neutralization of Input Used for LLM Prompting in GitLab
Published · Updated
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
21Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 7.3epss 0.6%
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:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Affected products
GitLab · GitLabRelated CVEs — GitLab
In the same product, most dangerous first.
CVE-2021-22205CRITICALCVE-2021-22205EPSS 99.7%KEVCVE-2026-85706CRITICALImproper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in GitLabEPSS 97.4%KEVCVE-2023-7028CRITICALWeak Password Recovery Mechanism for Forgotten Password in GitLabEPSS 94.5%KEVCVE-2021-22175MEDIUMCVE-2021-22175EPSS 53.4%KEVCVE-2021-39935MEDIUMCVE-2021-39935EPSS 36.1%KEVCVE-2026-97229CRITICALInteger Overflow or Wraparound in GitLabEPSS 27.7%KEV