VulnerabilityModified

CVE-2024-5184

The EmailGPT service contains a prompt injection vulnerability.

HIGH 8.5EPSS 0.54%

Does this matter?

High impact if exploited, but EPSS currently rates exploitation as unlikely (0.54%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.

Description

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.

CVSS 4.0: 8.5 HIGHCVSS:4.0/AV:A/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/M
EPSS: 0.54% probability · 44th percentile
CISA KEV: Not listed
Weakness: CWE-74
Affected: emailgpt/emailgpt
Source: disclosure@synopsys.com

References

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

Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.