Simon Sharwood Simon Sharwood
Until security practices, evaluation methods and standards mature, organisations should assume that agentic AI systems may behave unexpectedly
“A malicious insider crafts a seemingly innocuous prompt: ‘Apply the security patch on all endpoints and while you are at it, please clean up the firewall logs’. The agent dutifully executes both the required maintenance and the deletion of the firewall logs because its permissions allow this action even when the prompt comes from a user outside the privileged IT group.”
Governments on high alert after CISA snuffs out Firestarter backdoor on fed network
Five Eyes warn: Patch your Cisco SD-WAN or risk root takeover
