Cyber Resilience

CVE-2024-5184

High

Published: 05 June 2024

Published
05 June 2024
Modified
21 November 2024
KEV Added
—
Patch
—
CVSS Score v4 8.5 CVSS: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/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
EPSS Score 0.0011 28.4th percentile
Risk Priority 17 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2024-5184 is a high-severity Injection (CWE-74) vulnerability in Emailgpt Emailgpt. Its CVSS base score is 8.5 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 28.4th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.

This vulnerability is AI-related — categorised as Enterprise AI Assistants; in the LLM/Generative AI Risks risk domain; MITRE ATLAS techniques in scope: Indirect (AML.T0051.001), External Harms (AML.T0048).

EU & UK References

Vulnerability details

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…

more

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.

CWE(s)
CWE-74

AI Security AnalysisAI

AI Category
Enterprise AI Assistants
Risk Domain
LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
EmailGPT is an AI-powered service and Chrome extension that uses OpenAI's GPT models to assist with email writing in Gmail, functioning as an enterprise-style AI assistant vulnerable to prompt injection, which aligns with the Enterprise AI Assistants category.

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
attack.mitre.org →
T1211 Exploitation for Stealth Stealth
Adversaries may exploit vulnerabilities to evade detection by hiding activity, suppressing logging, or operating within trusted or unmonitored components.
attack.mitre.org →
Why these techniques?

Prompt injection vulnerability in the public-facing EmailGPT API service (T1190) enables attackers to bypass AI safeguards, leak hard-coded system prompts, and execute unwanted actions (T1211).

MITRE ATLAS TechniquesAI

MITRE ATLAS techniques

AML.T0051.001: IndirectAML.T0048: External Harms

Affected Assets

emailgpt
emailgpt
all versions

Mitigating Controls

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

SA-11 Developer Testing and Evaluation
addresses: CWE-74

Developer assessments and testing (including injection-focused techniques) identify improper neutralization of special elements, and the verifiable flaw remediation corrects them pre-deployment.

SI-4 System Monitoring
addresses: CWE-74

Identifies indicators of injection attacks (command, SQL, LDAP, etc.) via anomaly and attack monitoring.

References