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.
References
Link | Resource |
---|---|
https://www.synopsys.com/blogs/software-security/cyrc-advisory-prompt-injection-emailgpt.html | Third Party Advisory |
History
No history.
MITRE Information
Status: PUBLISHED
Assigner: SNPS
Published: 2024-06-05T17:52:13.608Z
Updated: 2024-06-06T13:12:29.208Z
Reserved: 2024-05-21T20:04:48.843Z
Link: CVE-2024-5184
JSON object: View
NVD Information
Status : Analyzed
Published: 2024-06-05T18:15:11.993
Modified: 2024-06-18T17:06:20.257
Link: CVE-2024-5184
JSON object: View
Redhat Information
No data.
CWE