LowVulnerabilityLLM-specific
CVE-2024-4099: GitLab EE AI feature hidden prompt injection through unsanitized content
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2024-4099
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.3%
Summary
CVE-2024-4099 affects GitLab EE from 16.0 before 17.2.8, from 17.3 before 17.3.4, and from 17.4 before 17.4.1. An AI feature read unsanitized content, which could let an attacker hide prompt injection. The weakness is classified as CWE-116, Improper Encoding or Escaping of Output.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Related items
- InfoTop agent skill security resources — November 2026Similar attack · Adversa AI Blog
- InfoHow to Turn AI Red Team Findings Into Runtime ControlsSimilar attack · Straiker Blog
- MediumDocker Sandboxes vulnerability lets AI agents access sensitive files outside their sandbox (CVE-2026-103916) | Endor LabsSimilar attack · Endor Labs Blog
- MediumFree the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak BundlesSimilar attack · Check Point Research
- InfoRight Tool, Wrong Parameters: Defending LLM Agents Against Parameter PoisoningSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)