Research
New Attack Type: ASCII Smuggling-AI Prompt Injection-Phishing Studied
Publication date unknown · Discovered circleid.com
Page published
Publication date unknown · First observed: 14 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
ASCII smuggling demonstrates how a prompt-injection technique against LLMs can be repurposed to evade phishing defenses, giving defenders a new input-sanitization gap to watch across both AI and email security.
Microsoft security researchers studied ASCII smuggling, a technique using invisible or special Unicode/ASCII characters, and documented how it is crossing over from AI prompt injection into phishing evasion. Hidden characters that embed instructions invisible to users can manipulate LLMs and also help malicious content slip past detection.