Questions
Common questions.
What is Indirect Prompt Injection?
Indirect prompt injection is an attack where malicious instructions are embedded in data the agent retrieves, such as documents, emails, or web pages, rather than in the user's direct input.
How does Indirect Prompt Injection work?
It is one of the hardest agent threats to defend against.
Which terms are related to Indirect Prompt Injection?
Closely related concepts include Spec-Driven Development, System Prompt, Agentic Coding, OWASP Top 10 for LLM Applications. Each is defined in the Prefactor glossary.
Keep reading