Research into Microsoft Entra has revealed that assistive AI agents can be manipulated to carry out malicious actions using a real user's permissions via delegated access flows. Security professionals must shift their detection strategies to correlate Purview, Graph API, and sign-in logs, as these "On Behalf of" attacks often bypass standard identity monitoring tools. Organizations should closely track the Add Delegated Permission Grant operation to identify when users unknowingly grant harmful scopes to compromised agents.
Read the full article at Cyber Security News
Want to create content about this topic? Use Nemati AI tools to generate articles, social posts, and more.





