InfraGuard

CVE-2026-96893

Improper Neutralization of Input Used for LLM Prompting in GitLab

7.3 CVSS 3.1EPSS 0.6%

Original 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 software

Details

Published
2026-10-13
Last modified
2026-10-14
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
CWE
CWE-74
EPSS (30-day exploit probability)
0.58% (percentile 48)

References

Track these versions on your own servers

InfraGuard collects installed software versions from every server and flags the ones with known vulnerabilities. Self-hosted — nothing leaves your network.

Weekly exploited-vulnerability digest

The KEV additions that matter for self-hosted servers, once a week. No other mail.

This product uses data from the NVD API but is not endorsed or certified by the NVD. CVE® is a registered trademark of The MITRE Corporation; CVE records are used under the CVE Program Terms of Use.