Microsoft and ServiceNow's exploitable agents reveal a growing - and preventable - AI security crisis
Briefly

Microsoft and ServiceNow's exploitable agents reveal a growing - and preventable - AI security crisis
"Once deployed on corporate networks, AI agents with broad access to sensitive systems of record can enable the sort of lateral movement across an organization's IT estate that most threat actors dream of. According to Jonathan Wall, founder and CEO of Runloop -- a platform for securely deploying AI agents -- lateral movement should be of grave concern to cybersecurity professionals in the context of agentic AI."
"Let's say a malicious actor gains access to an agent but it doesn't have the necessary permissions to go touch some resource. If, through that first agent, a malicious agent is able to connect to another agent with a [better] set of privileges to that resource, then he will have escalated his privileges through lateral movement and potentially gained unauthorized access to sensitive information."
"Meanwhile, the idea of agentic AI is so new that many of the workflows and platforms for developing and securely provisioning those agents have not yet considered all the ways a threat actor might exploit their existence. It's eerily reminiscent of software development's early days, when few programmers knew how to code software without leaving gaping holes through which hackers could drive a proverbial Mack truck."
Agentic AI systems with broad access to corporate systems of record enable lateral movement across IT estates, allowing one compromised agent to escalate privileges by interacting with higher-privileged agents. Such lateral movement can yield unauthorized access to sensitive information and mimic sophisticated threat actor behavior. Many agent development and provisioning workflows lack mature security controls and do not anticipate novel exploitation vectors. The nascent nature of agentic AI echoes early insecure software development practices, increasing systemic risk. Security teams should adopt least-privilege postures, rigorously control agent permissions and inter-agent communication, and harden provisioning platforms to limit attack surfaces.
#agentic-ai #lateral-movement #privilege-escalation #ai-security
Read at ZDNET
Unable to calculate read time
[
|
]