Standard
A 128-code-point block mirroring printable ASCII, created for language tagging, largely deprecated, and unrendered by most fonts and interfaces.
One developer's travel site deletes all 128 Unicode tag characters, plus zero-width and bidi controls, from user text before a model reads it. That closes the hidden-text channel outright, though typed-out injection still has to be caught by code checks downstream.
Reality
The Unicode tag block was a jailbreak trick before it was a spam trick. Microsoft's signature for it went from 21,000 hits in a day to more than 2.3 million three days later, and NFC normalization does not strip it.
Perspective Coverage
3 publishersReality
Microsoft's hunting signature for hidden AI instructions kept firing on ordinary bulk mail instead, where the invisible characters were doing nothing more ambitious than breaking a keyword, and failing at that.
Reality
Microsoft's hunt for email-borne prompt injection instead surfaced a three-month phishing campaign hiding tag characters inside words like funding, which puts both problems on one detection team's desk.
Reality
The Tags block was drafted for language codes, dropped, revived for flag emoji, then dropped again, and it still travels through every text field you run. That is why the answer is normalizing input rather than scanning it.
Reality