Restricted output disclosure via Boolean prompt injection
Published Mar 31, 2026 · Updated Mar 31, 2026
Prompt injection in 1MillionBot Millie Platform 3.6.0 allows remote attackers to obtain restricted responses through crafted chat prompts. Boolean prompts make an affirmative model response trigger an injected instruction, bypassing the chatbot's containment rules. No authentication or user interaction is required; impact is bounded to prohibited information, out-of-context behavior, and abuse of service resources.
Summary
What happened
Prompt injection in 1MillionBot Millie Platform 3.6.0 allows remote attackers to obtain restricted responses through crafted chat prompts. Boolean prompts make an affirmative model response trigger an injected instruction, bypassing the chatbot's containment rules. No authentication or user interaction is required; impact is bounded to prohibited information, out-of-context behavior, and abuse of service resources.
The record
- CVE
- CVE-2026-4399
- Published
- Mar 31, 2026
- Updated
- Mar 31, 2026
- Vendor
- 1MillionBot
- Product
- Millie Platform
- Classifications
- CWE-77, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 31, 2026CVE publishedPublication date reported by the CVE source.
- Mar 31, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=3.6.0
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo