← All labs
AI Sec Level 9 / 10 Medium

Adversarial Evasion

A toxicity classifier blocks certain messages. Get a blocked message through.

Content filter

This moderation model blocks abusive and attack-related messages. Get a message past it that a human would still read as one of those blocked words.

This is an isolated, intentionally-vulnerable sandbox. Data here is fake and scoped to you. The rest of Uncrypt Playground is not part of the target.