Improper Neutralization of Input Used for LLM Prompting in GitLab (GitLab GitLab)

CVE-2026-96893
HIGH 7.3

At a glance

Source
NVD
EPSS
EPSS 0.58 % · percentile 48 ()
State
PUBLISHED
Published
Updated
Assigner
GitLab
NVD status
Analyzed

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.

Weaknesses (CWE)

  • CWE-1427 — Improper Neutralization of Input Used for LLM Prompting
  • CWE-74 — Improper Neutralization of Special Elements in Output Used by a Downstream Component

References

Scores

VersionScoreVectorScored by
CVSS 3.1HIGH 7.3CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:NGitLab
CVSS 3.1HIGH 7.3CVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:NNVD · cve@gitlab.com (Secondary)

European references

CERT-FR advisories

Affected configurations (NVD CPE)

Affected products

ProductVersions
GitLab · GitLabaffected 19.1 < 19.2.8 ; affected 19.3 < 19.3.5 ; affected 19.4 < 19.4.2

Sources

SourceLicence
CVE List (CVEProject cvelistV5)CVE Program Terms of Use
EPSS (FIRST.org)FIRST — attribution requested
ENISA EUVDENISA — reproduction authorised, source acknowledged
CERT-FR (ANSSI)Licence Ouverte / Etalab 2.0
NVD (NIST) via fkie-cad/nvd-json-data-feedsPublic domain — this product uses data from the NVD API but is not endorsed or certified by the NVD