You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Open test set of .eml emails for checking how email security controls and AI mailbox assistants handle indirect prompt injection. It crosses three intents (system-prompt disclosure, data exfiltration, tool discovery) with three delivery methods (plaintext, hidden HTML, Base64), plus a benign control. All content is fictional and non-routable.
The first AI system developed by QMA Labs — an intelligent security analyzer designed to bridge human awareness and machine intelligence. Using Machine Learning, NLP, and threat intelligence, it detects phishing, spam, and social engineering threats in the evolving digital world.
A simulated secure email service using S/MIME for signing emails. The goal is to steal the admin's browser local storage flag by exploiting flaws in email parsing and rendering.