// For flags

CVE-2024-5184

Prompt Injection in EmailGPT

Severity Score

8.5
*CVSS v4

Exploit Likelihood

*EPSS

Affected Versions

*CPE

Public Exploits

0
*Multiple Sources

Exploited in Wild

-
*KEV

Decision

Track
*SSVC
Descriptions

The EmailGPT service contains a prompt injection vulnerability. The service uses an API service that allows a malicious user to inject a direct prompt and take over the service logic. Attackers can exploit the issue by forcing the AI service to leak the standard hard-coded system prompts and/or execute unwanted prompts. When engaging with EmailGPT by submitting a malicious prompt that requests harmful information, the system will respond by providing the requested data. This vulnerability can be exploited by any individual with access to the service.

El servicio EmailGPT contiene una vulnerabilidad de inyección rápida. El servicio utiliza un servicio API que permite a un usuario malintencionado inyectar un mensaje directo y hacerse cargo de la lógica del servicio. Los atacantes pueden aprovechar el problema obligando al servicio de inteligencia artificial a filtrar los mensajes estándar codificados del sistema y/o ejecutar mensajes no deseados. Al interactuar con EmailGPT enviando un mensaje malicioso que solicita información dañina, el sistema responderá proporcionando los datos solicitados. Esta vulnerabilidad puede ser aprovechada por cualquier persona con acceso al servicio.

*Credits: Mohammed Alshehri
CVSS Scores
Attack Vector
Adjacent
Attack Complexity
Low
Attack Requirements
None
Privileges Required
Low
User Interaction
None
System
Vulnerable | Subsequent
Confidentiality
High
High
Integrity
None
High
Availability
None
High
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
None
Availability
High
Attack Vector
Adjacent
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
None
Availability
None
* Common Vulnerability Scoring System
SSVC
  • Decision:Track
Exploitation
None
Automatable
No
Tech. Impact
Partial
* Organization's Worst-case Scenario
Timeline
  • 2024-05-21 CVE Reserved
  • 2024-06-05 CVE Published
  • 2024-06-19 EPSS Updated
  • 2024-08-01 CVE Updated
  • ---------- Exploited in Wild
  • ---------- KEV Due Date
  • ---------- First Exploit
CWE
  • CWE-74: Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
CAPEC
  • CAPEC-43: Exploiting Multiple Input Interpretation Layers
Affected Vendors, Products, and Versions
Vendor Product Version Other Status
Vendor Product Version Other Status <-- --> Vendor Product Version Other Status
Emailgpt
Search vendor "Emailgpt"
Emailgpt
Search vendor "Emailgpt" for product "Emailgpt"
--
Affected