Prompt Injection

What it is

Prompt injection is instructions hidden inside content an AI system reads, written to change what the system does rather than to inform it. It is the first entry in OWASP's Top 10 for LLM applications. The indirect form is the one that matters for published content: the instruction is planted in a web page, document or review that the system retrieves in the ordinary course of answering.

Why it matters

Any system that retrieves untrusted text can be steered by text inside it, and the defence is architectural rather than lexical — filtering for suspicious phrases fails because the attack space is the whole language. Treat retrieved content as data, never as instructions, and keep that boundary explicit in the system design. For a claim registry the specific exposure is that a third-party page could attempt to alter what an assistant reports about you.