CVE-2024-5184PoC(emailgpt / emailgpt)

LOWCVSS 9.1 · CRITICAL

Exploit discussion active in current signal (1 latest mentions)

Immediate actions

Hunt for exploitation attempts and persistence artifacts
Increase monitoring for publicly documented tradecraft
Track advisory updates for patch or workaround availability

Recommended action window: High priority (within 72h)

NVD 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.

emailgpt CVEs Back to dashboard

1.5/ 10 priority

Sources & remediation

Vendor / third-party advisories

Weakness type (CWE)

CWE-74

Priority

LOW

Exploitation

NONE

PoC

YES

Patch

NONE

Momentum

STABLE

Are you affected?

If you run products in this scope, you should treat this CVE as relevant to your environment.

emailgpt

Threat summary

Public PoC is present in monitored signal
2 mentions across 2 observed days
Momentum state: stable

What's happening

PoC mentioned or linked in 1 signal
Technical details provided in 1 signal
General: 1 classified signal
Peaked 1d ago at 1 mentions (2026-02-16); latest day: 1
2 total mentions across 2 days

Affected systems

Vendors

emailgpt

Products

emailgpt

1 version affected across 1 product

Deep dive

Activity timeline2 mentions / 2d

Signal classification2 categories

PoC

150.0%

General

150.0%

Classification over time

Date	Total	Labels

2026-02-16	1	PoC1
2026-09-08	1	General1

Full discourse2 posts

Slade 🛡️ LLM Hacker@llm_redteam30d
General
@ZealynxSecurity benchmark pass rates mean nothing when a 3-step tool chain leaks your db. cve-2024-5184. REPLY_RU <проценты прохождения бенчмарков ничего не значат, когда трехшаговая цепочка инструментов сливает вашу базу данных. cve-2024-5184.>
Post summary
The post references CVE‑2024‑5184 but only makes a vague claim that a 3‑step tool chain can leak a database, providing no technical, proof‑of‑concept, or exploitation details.
0001053
1.3K followersView on X
Michael Rouveure@MichaelRouveure235d
PoC
2/ PROMPT INJECTION → CODE EXECUTION The kill chain: → Agent processes untrusted content (email, webpage, file) → Hidden instructions trick the LLM → Agent runs malicious commands via exec → Malware downloaded, persistence established CVE-2024-5184 showed this with email assistants. "Inject My PDF" demonstrated it with resumes.
Post summary
CVE‑2024‑5184 enables prompt injection that allows code execution in email assistants; a proof‑of‑concept, “Inject My PDF,” demonstrated this using resumes, but no active exploitation or patch details are provided.
1000059
639 followersView on X

CPE platform detail1 entries

Part:

Vendor:

Product:

Version:

Target SW:

Target HW:

1 of 1 entries

Part	Vendor	Product	Version	Target SW	Target HW
App	emailgpt	emailgpt	-	-	-

Explore more

Back to dashboard emailgpt CVEs emailgpt vulnerabilities