A way to hide secret messages or instructions inside normal prompt text.
Prompt steganography is like a secret code in a school lunch menu. You see “Taco Tuesday,” but the AI sees “do the sneaky thing.”
People use it to hide attacks or break rules. It can also sneak out data. Agents may follow the code.
Prompt injection
Prompt steganography can hide injection instructions inside normal text.
Jailbreak
Secret codes can steer the model around safety rules.
Exfiltration
A hidden channel can quietly carry sensitive data out.
Agent Security
The risk grows when an agent follows the secret code.