Multiple vulnerabilities in 1millionbot Millie chatbot_CVE-2026-4399

8.7 / 10

HIGH

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N

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.

Basic Information

ID CVE-2026-4399

Source INCIBE

Published Mar 31, 2026 at 10:10

Modified Mar 31, 2026 at 13:31

Affected Product

Vendor 1millionbot

Product Millie chat

Version 3.6.0

Affected Versions 1millionbot Millie chat 3.6.0

CWE Classification

CWE-1427

References

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

{
    "lastseen": "",
    "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.",
    "published": "2026-03-31T10:10:08.529Z",
    "modified": "2026-03-31T13:31:06.385Z",
    "type": "cve",
    "title": "Multiple vulnerabilities in 1millionbot Millie chatbot",
    "source": "INCIBE",
    "references": "https://www.incibe.es/en/incibe-cert/notices/aviso/multiple-vulnerabilities-1millionbot-millie-chatbot",
    "id": "CVE-2026-4399",
    "bulletinFamily": "",
    "cwe": [
        "CWE-1427"
    ],
    "cvelist": null,
    "sourceData": "1millionbot Millie chat 3.6.0",
    "sourceHref": "",
    "cvss": {
        "score": 8.7,
        "severity": "HIGH",
        "vector": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N",
        "version": "4.0"
    },
    "cvss2": [],
    "cvss3": {
        "version": "",
        "vectorString": "",
        "baseScore": 0,
        "baseSeverity": "",
        "attackVector": "",
        "attackComplexity": "",
        "privilegesRequired": "",
        "userInteraction": "",
        "scope": "",
        "confidentialityImpact": "",
        "integrityImpact": "",
        "availabilityImpact": "",
        "cvssV3": {
            "version": "",
            "vectorString": "",
            "baseScore": 0,
            "baseSeverity": "",
            "attackVector": "",
            "attackComplexity": "",
            "privilegesRequired": "",
            "userInteraction": "",
            "scope": "",
            "confidentialityImpact": "",
            "integrityImpact": "",
            "availabilityImpact": ""
        }
    },
    "href": "",
    "category_name": "CVE",
    "post_link": "",
    "product": "Millie chat",
    "version": "3.6.0",
    "vendor": "1millionbot",
    "ai_description": "",
    "ai_severity": "",
    "ai_vendor": "",
    "ai_product": "",
    "ai_version": "",
    "ai_score": 0
}