# CVE-2026-4399: Multiple vulnerabilities in 1millionbot Millie chatbot

> Attackers can use prompt injection to bypass restrictions, execute unauthorized tasks, and access prohibited information via the Millie chatbot.

- **Severity:** High 8.7 (`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`)
- **Exploited in the wild:** Not known
- **Login needed:** Not needed
- **Attackable:** Over the internet
- **Victim action needed:** Not needed
- **Fix available:** No
- **Published:** 31 Mar 2026
- **Updated:** 31 Mar 2026
- **Also known as:** GHSA-7649-76jc-fc5r

## What is CVE-2026-4399?

CVE-2026-4399 is a high-severity code injection vulnerability in 1millionbot Millie chat, published on 31 Mar 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.

### Official 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.

Weakness: CWE-77 (Improper Neutralization of Special Elements used in a Command), CWE-1427 (Improper Neutralization of Input Used for LLM Prompting)

## Which versions are affected by CVE-2026-4399?

It affects 1 product.


Products: 1millionbot Millie Chatbot.

## How do I fix CVE-2026-4399?

No fix has been published for CVE-2026-4399 yet. Limit exposure of the affected software until one is available.

## Is CVE-2026-4399 being exploited?

There is no known exploitation of CVE-2026-4399 in the wild and no public exploit code.

## Other vulnerabilities in 1millionbot Millie chat

- [CVE-2026-4400](https://insights.sbomify.com/CVE-2026-4400/): Multiple vulnerabilities in 1millionbot Millie chatbot (high 7.0)

## Fix prompt for AI coding agents

```text
Check this codebase for CVE-2026-4399 and fix it if it is affected.

What it is: CVE-2026-4399 is a high-severity code injection vulnerability in 1millionbot Millie chat, published on 31 Mar 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Exploitation: There is no known exploitation of CVE-2026-4399 in the wild and no public exploit code.

Affected product: 1millionbot Millie chat. No package-level version data is available, so check the vendor advisory linked from the reference page.

Task:
1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.
2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.
3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.
4. Run the tests and summarise what changed and why.
5. If nothing in the project is affected, say so and change nothing.

Reference: https://insights.sbomify.com/CVE-2026-4399/ (Markdown: https://insights.sbomify.com/CVE-2026-4399/index.md)
```

## Sources

- CVE record: https://www.cve.org/CVERecord?id=CVE-2026-4399
- NVD: https://nvd.nist.gov/vuln/detail/CVE-2026-4399
- OSV: https://osv.dev/vulnerability/CVE-2026-4399

---
From sbomify Insights: https://insights.sbomify.com/CVE-2026-4399/
Summaries are generated and may contain mistakes; the official description above is the record.