CVE-2026-4399

Signals

NVD · CVE-2026-64604 · In the Linux kernel, the following vulnerability has been resolved: KVM: VMX: Grab vmcs12 on CR8 interception update iff vCPU is in guest mode When updating CR8NVD · CVE-2026-64603 · In the Linux kernel, the following vulnerability has been resolved: platform/x86: intel-hid: Protect ACPI notify handler against recursion Since commit e2ffcda1NVD · CVE-2026-64602 · In the Linux kernel, the following vulnerability has been resolved: iio: adc: spear: Initialize completion before requesting IRQ In the report from Jaeyoung ChuNVD · CVE-2026-64601 · In the Linux kernel, the following vulnerability has been resolved: ALSA: us144mkii: capture_urb_complete: redundant usb_anchor_urb corrupts anchor list on eachCISA KEV · CVE-2026-63077 · 9.8 · JetBrains TeamCity Deserialization of Untrusted Data Vulnerability · Added 2026-08-05 · Due 2026-08-08CISA KEV · CVE-2026-18556 · 7.4 · N-able N-central Authentication Bypass Using an Alternate Path or Channel Vulnerability · Added 2026-08-04 · Due 2026-08-07NVD · CVE-2026-64604 · In the Linux kernel, the following vulnerability has been resolved: KVM: VMX: Grab vmcs12 on CR8 interception update iff vCPU is in guest mode When updating CR8NVD · CVE-2026-64603 · In the Linux kernel, the following vulnerability has been resolved: platform/x86: intel-hid: Protect ACPI notify handler against recursion Since commit e2ffcda1NVD · CVE-2026-64602 · In the Linux kernel, the following vulnerability has been resolved: iio: adc: spear: Initialize completion before requesting IRQ In the report from Jaeyoung ChuNVD · CVE-2026-64601 · In the Linux kernel, the following vulnerability has been resolved: ALSA: us144mkii: capture_urb_complete: redundant usb_anchor_urb corrupts anchor list on eachCISA KEV · CVE-2026-63077 · 9.8 · JetBrains TeamCity Deserialization of Untrusted Data Vulnerability · Added 2026-08-05 · Due 2026-08-08CISA KEV · CVE-2026-18556 · 7.4 · N-able N-central Authentication Bypass Using an Alternate Path or Channel Vulnerability · Added 2026-08-04 · Due 2026-08-07

CVE Database · CVE-2026-4399

CVE-2026-4399

· HIGHAnalyzed

CVSS v3.1

7.5

CVSS v4.0

8.7

EPSS

0.27%

Published

Mar 31, 2026

Modified

Apr 13, 2026

Public PoC / Exploit

All weaponized →

No public PoC or exploit code indexed for this CVE.

Links to public security research (Exploit-DB, Nuclei, Trickest, GitHub) for defensive use only.

Description

Prompt injection vulnerability in 1millionbot Millie chatbot that occurs when a user manages to evade chat restrictions using Boolean prompt injection techniques (formulating a question in such a way that, upon receiving an affirmative response ('true'), the model executes the injected instruction), causing it to return prohibited information and information outside its intended context. Successful exploitation of this vulnerability could allow a malicious remote attacker to abuse the service for purposes other than those originally intended, or even execute out-of-context tasks using 1millionbot's resources and/or OpenAI's API key. This allows the attacker to evade the containment mechanisms implemented during LLM model training and obtain responses or chat behaviors that were originally restricted.

CVSS Vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N

Weaknesses (CWE)

CWE-77

Affected Products (1)

1millionbot · millie_chatbot (up to 3.6.0)vulnerable

References (1)

https://www.incibe.es/en/incibe-cert/notices/aviso/multiple-vulnerabilities-1millionbot-millie-chatbot

Third Party Advisory

KEV Catalog EPSS Scores Vendors All CVEs