AML.T0065
LLM Prompt Crafting
Description
Adversaries may use their acquired knowledge of the target generative AI system to craft prompts that bypass its defenses and allow malicious instructions to be executed. The adversary may iterate on the prompt to ensure that it works as-intended consistently.
Honesty-tier rationale
Attacker preparation (infrastructure, accounts, publishing poisoned models/data). Actually producing poisoned artifacts is exactly what an educational site must not do — delivered as an explainer.