
What Is Indirect Prompt Injection and How Does It Reach AI Agents?
An instruction a third party plants in content an agent reads, such as an email, file, web page or tool result, so the attacker never touches the prompt.
Research topic
Research on InjecAgent: AI agent security, tokenization and checks for sensitive data access before allowing enterprise workflows to run.

An instruction a third party plants in content an agent reads, such as an email, file, web page or tool result, so the attacker never touches the prompt.