security: ASCII smuggling crosses over from AI prompt injection to phishing evasion

· Sujith Quintelier · Sept. 3, 2026, 8:42 p.m.
Summary
The blog post discusses a new technique called 'ASCII smuggling' that has transitioned from concealing prompts for AI to evading email filters, facilitating phishing attempts. The content highlights the implications of this method as identified by Microsoft Security Blog.
AUTHOR
Sponsored
Zulip logo Zulip
Organized team chat for people who take work seriously. Topic-based threading keeps conversations focused.
Try Zulip
Become a sponsor →