Glossary › Safety

Prompt Injection

Attack where adversarial text in user input attempts to override system instructions. Types: direct (ignore above), indirect (hidden in retrieved docs). Defense: input validation, separate channels.

Where this is taught

• Prompt Injection Basics — Phase 8: Traps, Judgment & Staying Current
• LLM01: Prompt Injection — Phase 1: OWASP Top 10 for LLM Applications
• Project: Prompt Injection Detector + Jailbreak Library — Phase 2: Prompt Injection & Jailbreaking
• Indirect Injection & Cross-Domain Prompt Injection (XPIA) — Phase 2: Prompt Injection & Jailbreaking
• Building a Multi-Layer Prompt Injection Detector — Phase 2: Prompt Injection & Jailbreaking
• Guardrails: Input/Output Safety for LLM Applications — Phase 8: Evaluation, Safety & Observability

Related terms

Guardrails · Red Teaming

More in Safety

Guardrails · Red Teaming · Constitutional AI · PII Detection

Learn this by building

DeVenture Academy teaches AI engineering through projects — every lesson is paired with a hands-on lab you run on your own machine with real tools.

Create a free account — the opening phases of 24 of 30 courses are free, no credit card. Or see Pro pricing.

All courses · Pricing · About · FAQ · Glossary