Indirect Prompt Injection in Web Content Targets AI Agents

IntroductionAI agents are increasingly changing how users interact with web content, making the content itself a growing attack surface for threat actors. Just as a human user can be socially engineered through phishing, AI agents are also susceptible to similar attacks. Indirect prompt injection (IPI) is an example of these types of attacks that embed malicious instructions in the content retrieved by an AI agent (websites, documents, email, etc.) to influence the agent’s…

Diamond Model