CVE-2026-96893Improper Neutralization of Input Used for LLM Prompting in GitLab
Updated under an hour ago ()
Does this affect you?
It affects GitLab. Add what you run to find out whether that includes you.
EPSS puts the chance of exploitation in the next 30 days at 0.53%, higher than 44% of scored CVEs.
Do this next
Free account, 1 product
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 (v3.1, CNA)CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
- Weakness (CWE)
- CWE-1427
- Known exploited
- Not in CISA's KEV catalog
- EPSS (exploitation in the next 30 days)
- 0.53% (percentile 44)
- Assigned by
- GitLab
- NVD analysis
- Analyzed
- Record last updated
- Oct 14, 2026
- First seen by InfoSec Signals
- Oct 13, 2026
Affected products
GitLab GitLab gitlab:gitlab | from 19.1 before 19.2.8; from 19.3 before 19.3.5; from 19.4 before 19.4.2 | CNA record |
gitlab gitlab gitlab:gitlab | from 19.1.0 before 19.2.8; from 19.3.0 before 19.3.5; from 19.4.0 before 19.4.2 | NVD |
References
- https://gitlab.com/gitlab-org/gitlab/-/work_items/607968issue-tracking
- https://docs.gitlab.com/releases/patches/patch-release-gitlab-19-4-2-released/release-notes, vendor-advisory
The CVE record on cve.org NVD's entry
The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.