AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
prompt injection — An attack that hides instructions in content an AI will read — a webpage, email, or document — tricking it into following the attacker instead of the user.
Why it matters
Agents that pass user input verbatim can now be screened for injection patterns before the request leaves the gateway, and runaway loops can be capped per key or per member with hard 402 responses.
