CVE-2024-5184

System-prompt disclosure and API abuse via prompt injection

Published Jun 5, 2024 · Updated Aug 1, 2024

Prompt injection in the EmailGPT API main branch allows attackers with service access to disclose system prompts and run unwanted prompts. The API places attacker-supplied prompt text into the model's instruction flow without preventing it from overriding hard-coded service logic. Any individual with service access can request harmful information, expose intellectual property, or drive repeated pay-per-use calls that interrupt service and cause financial loss.

CVSS severity8.5
High
EPSS probability0.54%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Prompt injection in the EmailGPT API main branch allows attackers with service access to disclose system prompts and run unwanted prompts. The API places attacker-supplied prompt text into the model's instruction flow without preventing it from overriding hard-coded service logic. Any individual with service access can request harmful information, expose intellectual property, or drive repeated pay-per-use calls that interrupt service and cause financial loss.

The record

CVE
CVE-2024-5184
Published
Jun 5, 2024
Updated
Aug 1, 2024
Vendor
Unknown vendor
Product
Unknown product
Classifications
CWE-74, CAPEC-43
Attack vector
Unavailable
Privileges
Unavailable

Timeline

How it unfolded

  1. Jun 5, 2024CVE publishedPublication date reported by the CVE source.
  2. Aug 1, 2024Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Affected buildAffected product and version details are unavailable.

What conditions does exploitation require?

Attack vectorUnavailable in this record.
Required privilegesUnavailable in this record.

What is affected?

Affected products and versions are unavailable in this record.

Published CVSS scores

8.5SynopsysCVSS:4.0/AV:A/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:H/SI:H/SA:H
6.5SynopsysCVSS:3.1/AV:A/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
9.1NIST NVDCVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
9.4NIST NVDAV:N/AC:L/Au:N/C:C/I:N/A:C

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
VectorUnavailable
PrivilegesUnavailable
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-74Improper Neutralization of Special Elements in Output Used by a Downstream Component ('Injection')
CAPEC-43Exploiting Multiple Input Interpretation Layers

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo