+- Hack Forums (https://hackforums.net)
+-- Forum: General Topics (https://hackforums.net/forumdisplay.php?fid=7)
+--- Forum: World (https://hackforums.net/forumdisplay.php?fid=445)
+---- Forum: News and Happenings (https://hackforums.net/forumdisplay.php?fid=89)
+---- Thread: ServiceNow AI Agents Can Be Tricked Into Acting Against Each Other via Second-Order (/showthread.php?tid=6314722)
ServiceNow AI Agents Can Be Tricked Into Acting Against Each Other via Second-Order - Stanley - Nov 29, 2025
ServiceNow AI Agents Can Be Tricked Into Acting Against Each Other via Second-Order
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
https://thehackernews.com/2025/11/servicenow-ai-agents-can-be-tricked.html