New exploit found in ServiceNow’s AI agents can be tricked to act against each other

A new exploit in ServiceNow’s Now Assist platform can allow malicious actors to manipulate its AI agents into performing unauthorized actions, as detailed by SaaS security firm AppOmni. Default configurations in the software, which enable agents to discover and collaborate with one another, can be weaponized to launch prompt injection attacks far beyond a single […] source: https://www.cryptopolitan.com/servicenows-ai-agents-coordinated-attacks/