Executive Summary

Informations
Name CVE-2024-5184 First vendor Publication 2024-06-05
Vendor Cve Last vendor Modification 2024-11-21

Security-Database Scoring CVSS v3

Cvss vector : CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
Overall CVSS Score 9.1
Base Score 9.1 Environmental Score 9.1
impact SubScore 5.2 Temporal Score 9.1
Exploitabality Sub Score 3.9
 
Attack Vector Network Attack Complexity Low
Privileges Required None User Interaction None
Scope Unchanged Confidentiality Impact High
Integrity Impact None Availability Impact High
Calculate full CVSS 3.0 Vectors scores

Security-Database Scoring CVSS v2

Cvss vector :
Cvss Base Score N/A Attack Range N/A
Cvss Impact Score N/A Attack Complexity N/A
Cvss Expoit Score N/A Authentication N/A
Calculate full CVSS 2.0 Vectors scores

Detail

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.

Original Source

Url : http://cve.mitre.org/cgi-bin/cvename.cgi?name=CVE-2024-5184

CWE : Common Weakness Enumeration

% Id Name
100 % CWE-74 Failure to Sanitize Data into a Different Plane ('Injection')

CPE : Common Platform Enumeration

TypeDescriptionCount
Application 1

Sources (Detail)

https://www.synopsys.com/blogs/software-security/cyrc-advisory-prompt-injecti...
Source Url

Alert History

If you want to see full details history, please login or register.
0
1
2
3
Date Informations
2024-11-25 09:25:12
  • Multiple Updates
2024-06-18 21:34:15
  • Multiple Updates
2024-06-06 21:27:26
  • Multiple Updates
2024-06-06 00:27:25
  • First insertion