01Explain direct vs indirect prompt injection, and how each one actually breaks an LLM application.▼easy★ EssentialOpenAIMicrosoftGlean2 repliesunlockedOWASP's LLM01 is the opening question of nearly every AI security screen. Most candidates can define direct injection; the ones who get hired explain why indirect injection is the one that ruins enterprise deployments.Open full answer →
02How is a jailbreak different from prompt injection? Give an example of each from a real application.▼easyAnthropicMicrosoftScale1 repliesunlockedCandidates use these terms interchangeably and security interviewers notice immediately. The distinction, whose policy is being violated, drives completely different defenses, and that's the actual question.Open full answer →
03Why do system prompts leak, and what should never be in one?▼easyOpenAIAnthropicSalesforce1 repliesunlockedOWASP made system prompt leakage its own category (LLM07) because teams keep treating prompts as secrets. The strong answer flips the premise: design so extraction doesn't matter.Open full answer →
