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
Read more https://thehackernews.com/2025/11/servicenow-ai-agents-can-be-tricked.html
