VulnerabilityPublished 31 Mar 2026

CVE-2026-4399: 1millionbot Millie chat · Improper neutralization of input used for LLM prompting

Affects 1millionbot Millie chatSource CVE Database V5

Compare

Not known to be exploited · CVSS 8.7 High.

Data as of 29 Oct 2026, 19:04 UTC

CVSS 4.0 base score

8.7High

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.2% chance of exploitation in 30 days – higher than 19% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

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

Attack Vector: Network
Attack Complexity: Low
Attack Requirements: None
Privileges Required: None
User Interaction: None
Vulnerable system confidentiality: High
Vulnerable system integrity: None
Vulnerable system availability: None
Subsequent system confidentiality: None
Subsequent system integrity: None
Subsequent system availability: None

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable system is bound to the network stack and the set of possible attackers extends beyond the other options listed below, up to and including the entire Internet. Such a vulnerability is often termed “remotely exploitable” and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: The attacker must take no measurable action to exploit the vulnerability. The attack requires no target-specific circumvention to exploit the vulnerability. An attacker can expect repeatable success against the vulnerable system.
Attack Requirements: None: The successful attack does not depend on the deployment and execution conditions of the vulnerable system. The attacker can expect to be able to reach the vulnerability and execute the exploit under all or most instances of the vulnerability.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files of the vulnerable system to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without interaction from any human user, other than the attacker.
Vulnerable system confidentiality: High: There is a total loss of confidentiality, resulting in all information within the Vulnerable System being divulged to the attacker. Alternatively, access to only some restricted information is obtained, but the disclosed information presents a direct, serious impact. For example, an attacker steals the administrator's password, or private encryption keys of a web server.
Vulnerable system integrity: None: There is no loss of integrity within the Vulnerable System.
Vulnerable system availability: None: There is no impact to availability within the Vulnerable System.
Subsequent system confidentiality: None: There is no loss of confidentiality within the Subsequent System or all confidentiality impact is constrained to the Vulnerable System.
Subsequent system integrity: None: There is no loss of integrity within the Subsequent System or all integrity impact is constrained to the Vulnerable System.
Subsequent system availability: None: There is no impact to availability within the Subsequent System or all availability impact is constrained to the Vulnerable System.

Definitions: FIRST CVSS v4.0 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 31 Mar 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 29 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Affected software

Product	Affected	Fixed in
1millionbotMillie chat	Affected =3.6.0	Fixed in–
npm1millionbot/millie-chat`pkg:npm/1millionbot/millie-chat`Other threats	Affected =3.6.0	Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Until a fix is released, users should exercise caution when deploying or exposing the affected version (3.6.0) of 1millionbot Millie chat and monitor vendor communications for updates.

Description

CVE-2026-4399 is a prompt injection vulnerability in the 1millionbot Millie chatbot version 3.6.0. It allows attackers to bypass chat restrictions by crafting inputs that cause the model to execute unintended instructions, potentially revealing prohibited information or performing out-of-context tasks. This vulnerability can lead to abuse of the chatbot service and misuse of associated resources, including OpenAI's API key. The vulnerability has a high severity score of 8.7 but no known exploits in the wild have been reported. No official patch or remediation guidance is currently available.

Impact

Successful exploitation allows remote attackers to bypass implemented containment mechanisms in the LLM, leading to unauthorized disclosure of restricted information and execution of unintended commands. This could result in misuse of the chatbot service and its resources, including unauthorized use of OpenAI's API key. There are no reports of active exploitation in the wild at this time.

Summary

The vulnerability identified as CVE-2026-4399 in 1millionbot Millie chat version 3.6.0 involves improper neutralization of input used for large language model (LLM) prompting (CWE-1427). Attackers can use Boolean prompt injection techniques to evade chat restrictions, causing the chatbot to execute injected instructions when it receives an affirmative response. This results in the chatbot returning information or performing tasks outside its intended scope, potentially abusing the service and associated resources such as OpenAI's API key. The CVSS 4.0 base score is 8.7, indicating high severity, with network attack vector, low attack complexity, no privileges or user interaction required, and high impact on confidentiality.

CWE-1427Improper Neutralization of Input Used for LLM Prompting (opens in a new tab)
Base weakness
The product uses externally-provided data to build prompts provided to large language models (LLMs), but the way these prompts are constructed causes the LLM to fail to distinguish between user-supplied inputs and developer provided system directives.
Architecture and Design
LLM-enabled applications should be designed to ensure proper sanitization of user-controllable input, ensuring that no intentionally misleading or dangerous characters can be included.
Implementation
LLM prompts should be constructed in a way that effectively differentiates between user-supplied input and developer-constructed system prompting to reduce the chance of model confusion at inference-time.
Architecture and Design
LLM-enabled applications should be designed to ensure proper sanitization of user-controllable input, ensuring that no intentionally misleading or dangerous characters can be included.
OWASP Cheat Sheets
Abuse Case (opens in a new tab)
Deserialization (opens in a new tab)
OWASP ASVS 4.0.3
V1.5.1 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

incibe.es/en/incibe-cert/notices/aviso/multiple-vulnerabilities-1millionbot-millie-chatbot (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 7 Apr 2026, 10:57 UTC

WeaknessesCWE-1427

Technical details

References

Community reviews

Related threats