PoC Monitor
← All CVEs
CVE-2026-96893published 13 Oct 2026 01:05 UTCData: JSON · API

GitLab

Improper Neutralization of Input Used for LLM Prompting in GitLab

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.

First public PoC None yetno public PoC found
Public PoCs00 on GitHub
CVSS7.3high · scored by CNA · CWE-1427
CISA KEV Not listednot known exploited

Affected versions and mitigation

From the CVE record and the vendor's references.

Affected

GitLab GitLab
  • >= 19.1, < 19.2.8
  • >= 19.3, < 19.3.5
  • >= 19.4, < 19.4.2

Fixed in 19.2.8, 19.3.5, 19.4.2

Mitigation

Upgrade to versions 19.2.8, 19.3.5, 19.4.2 or above.

Timeline

Days relative to CVE publication
-2t=0+2+4+6+8CVE published13 Oct 2026 · t = 0

No public PoC found yet; not in CISA KEV.

PoC repositories

Found on GitHub.

No PoC repositories found yet.