MediumVulnerabilityLLM-specific
CVE-2024-5184: EmailGPT prompt injection that leaks system prompts and runs unwanted prompts
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2024-5184
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.5%
Summary
CVE-2024-5184 affects the EmailGPT service, which relies on an API service that lets a malicious user inject a direct prompt and take over the service logic. An attacker can force the AI service to leak its hard-coded system prompts and/or execute unwanted prompts, and any individual with access to the service can exploit it.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
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)