CVE-2026-4399
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.
Scoring
- Severity
- HIGH
- CVSS base score
- 8.7
- CVSS 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
- EPSS probability
- 0.27%
- CWE
- CWE-1427
- Published
- 2026-03-31
- Last modified
- 2026-03-31
Affected products
- 1millionbot Millie chat
Weakness type
Related vulnerabilities
- CVE-2026-70331 — Microsoft Edge for iOS Spoofing Vulnerability
- CVE-2026-78379 — Consent bypass in python_repl tool via batch kwargs forwarding in Amazon Strands Agents Tools
- CVE-2026-75130 — Context7 2.1.2 Prompt Injection via Custom AI Instructions
- CVE-2026-21832 — HCL AION is affected by multiple security vulnerabilities.
- CVE-2026-18733 — Prompt injection bypasses shell tool consent gate in Strands Agents Tools
- CVE-2026-15077 — Improper Neutralization of Input Used for LLM Prompting in GitLab
- CVE-2026-46580 — In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in...
- CVE-2026-44688 — In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory...