Every CVE Search/ Get API key

CVE-2026-96893

Improper Neutralization of Input Used for LLM Prompting in GitLab

7.3 HighFix available

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.

Attack profile

How easy it is to exploit

Attack vector
Network
Complexity
Low
Privileges needed
Low
User interaction
Required

What an attacker can affect

Confidentiality
High
Integrity
High
Availability
None

Exploit likelihood

0.58%Unchanged since Oct 13, 2026
90%50%10%1%

What each source reports

CVE List Score used 7.3

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.

Record
CVE-2026-96893
CVSS 3.1
7.3 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Weakness
CWE-1427
Updated
2026-11-02
EUVDEUVD-2026-98213 7.3

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.

Record
EUVD-2026-98213
CVSS 3.1
7.3 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Updated
2026-11-02
GitHub AdvisoriesGHSA-5vgp-j37h-7wfx 7.3

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3...

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.

Record
GHSA-5vgp-j37h-7wfx
CVSS 3.1
7.3 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Weakness
CWE-74
Updated
2026-11-02
NVD 7.3

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.

Record
CVE-2026-96893
CVSS 3.1
7.3 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Weakness
CWE-74
Updated
2026-11-02
OSV 7.3

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.

Record
CVE-2026-96893
CVSS 3.1
7.3 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Weakness
CWE-1427
Updated
2026-11-02
OSVUBUNTU-CVE-2026-96893 7.3

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.

Record
UBUNTU-CVE-2026-96893
CVSS 3.1
7.3 HighCVSS:3.1/AV:N/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N
Updated
2026-11-02
OSVBIT-gitlab-2026-96893 No score

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.

Record
BIT-gitlab-2026-96893
Updated
2026-11-02

Affected products

Affected packages

Affected packages
PackageAffectedFixed
gitlab
Bitnami
 19.1.0 up to 19.2.8, 19.3.0 up to 19.3.5, 19.4.0 up to 19.4.2
19.2.819.3.519.4.2
gitlab
Ubuntu:16.04:LTS
 All versions, plus listed versions
8.4.3+dfsg-98.4.3+dfsg-128.5.8+dfsg-5
 None known

History

History
RecordedChangedSources
first indexedCVE List, EUVD, GitHub Advisories, NVD, OSV

Dates are when Every CVE recorded each change. Upstream dates may differ.

In short

CVE-2026-96893 is a high vulnerability (CVSS 7.3) in Gitlab, published October 13, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.58%, the 48th percentile. Fixed in gitlab 19.2.8.

References

Pages All vulnerabilities Browse Docs Sources Guide Get API key
MoveEnter Open