AI RESEARCH
How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition
arXiv CS.AI
•
ArXi:2603.15714v1 Announce Type: cross LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness.