Robot Explains Gallery
A kid-friendly visual interpretation of the OWASP Top 10 for LLM applications.
When sneaky instructions try to trick the robot into breaking its rules.
View poster →
When the robot accidentally spills a secret it should have kept.
View poster →
Sometimes bad ingredients sneak into the robot's toolbox.
View poster →
When the robot learns from bad examples and picks up wrong ideas.
View poster →
When an app trusts the robot's answer without double-checking it.
View poster →
When the robot is allowed to do more than it really should.
View poster →
When the robot's secret instructions slip out for everyone to see.
View poster →
When the robot's memory lookup gets confused or tricked.
View poster →
When the robot says something wrong but sounds very sure.
View poster →
When the robot uses way too much and slows everything down.
View poster →