CVE-2026-96893BIT-GITLAB-2026-96893
Improper Neutralization of Input Used for LLM Prompting in GitLab
- Published
- Last modified
- Where the record stands: published, rejected by its publisher, or superseded by another id.What do these mean? →
- published
- Whether CISA lists it in its Known Exploited Vulnerabilities catalog: proof that attackers are using it.What do these mean? →
- Not listed in CISA KEV
- Fix
- Fixed in 19.2.8, 19.3.5, 19.4.2
- Whether working attack code is public (Exploit-DB, Metasploit, Nuclei or GitHub). Public code makes attacks easier.What do these mean? →
- None on Exploit-DB, Metasploit or GitHub
CISA's decision points: whether it is exploited, whether attacks can be automated, and how much control an attacker gets. Assessed (SSVC 2.0.3).What do these mean? →
- Exploitation: none
- Automatable: no
- Technical impact: total
Summary
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.
Timeline
- CVE published
- CISA SSVC assessment
Exploitation: none · Automatable: no · Technical impact: total
- Record last updated
Affected versions
- GitLab GitLab
From 19.1 · fixed in 19.2.8; From 19.3 · fixed in 19.3.5; From 19.4 · fixed in 19.4.2
- gitlabBitnami
From 19.1.0 · fixed in 19.2.8; From 19.3.0 · fixed in 19.3.5; From 19.4.0 · fixed in 19.4.2