Malicious actors can exploit default configurations in ServiceNow’s Now Assist generative artificial intelligence (AI) platform and leverage its agentic capabilities to conduct prompt injection attacks.
The second-order prompt injection, according to AppOmni, makes use of Now Assist’s agent-to-agent discovery to execute unauthorized actions, enabling attackers to copy and exfiltrate sensitive
ServiceNow AI Agents Can Be Tricked Into Acting Against Each Other via Second-Order Prompts
