CVE-2024-5184

low-risk

Published 2024-06-05

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.

Do I need to act?

0.11% chance of exploitation

EPSS score — low exploit probability

Not on CISA KEV list

No confirmed active exploitation reported to CISA

Patch status unknown

Check vendor advisories for fix availability and mitigation guidance

CVSS 6.5/10 Medium

ADJACENT_NETWORK / LOW complexity

Affected Products (1)

Emailgpt

Affected Vendors

Emailgpt

References (2)

Third Party Advisory https://www.synopsys.com/blogs/software-security/cyrc-advisory-prompt-injection-...

/ 100

low-risk

Severity 21/34 · High

Exploitability 0/34 · Minimal

Exposure 5/34 · Minimal