A practitioner's view of when coding agents became reliable, how they handle persistent problem solving, and the security risks of prompt injectionAn 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.Full definition → and rogue agents.
Terms in this piece · Glossary
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.