A clever technique used to hide malicious prompts in attacks on AI agents has been adopted by spammers to evade filters on email platforms that are designed to flag unwanted messages used in mass campaigns.
The technique is broadly known as ASCII smuggling. It gained attention two years ago as a means of making a class of AI attack known as prompt injections more stealthy. Malicious instructions embedded in emails or other untrusted content to be processed by an LLM aren’t written in ordinary text. Instead, they’re rendered by a special range of Unicode tags. For example, the tag point U+E0041 mirrors “A,” and U+E0061 mirrors “a.”
No longer just for obscuring prompt injections
The block of 128 tags mimics a portion of the American Standard Code for Information Interchange almost perfectly, with one major difference: the characters they encode are readable by computers but, by design, are almost completely invisible to humans. By expressing the malicious prompts in these tags, LLMs detect the instructions, but people reading the email never see them. There’s much more about ASCII smuggling here.
Tesla’s Cybercab has been deployed, and it’s already under investigation
September 5, 2026
The weird and wonderful headphones of CanJam 2026
September 5, 2026
iQOO போட்டான் பாரு.. 8400mAh பேட்டரி.. 100W சார்ஜிங்.. AMOLED டிஸ்பிளே.. 50MP கேமரா.. எந்த மாடல்?
September 5, 2026
OpenAI admits to German wiki ‘incident’
September 5, 2026
ஆர்டர் பிச்சிக்குது.. ரூ.1,300 ஆஃபர் ரேட்ல 7200mAh பேட்டரி.. 44W ஃபாஸ்ட் சார்ஜிங்.. 50MP கேமரா.. எந்த மாடல்?
September 5, 2026
Robotaxis enter their villain era
September 5, 2026
Taylor dominates Pili in final fight of career at Croke Park
September 5, 2026
'We've got one hand on it!' – Partington on Super League title chances
September 5, 2026
Wozoyo Pure Air PA1 Review: Compact Budget Air Purifier With a Few Missing Features
September 5, 2026
Papers: Saudi move most likely for Richarlison
September 5, 2026