Attention: You are using an outdated browser, device or you do not have the latest version of JavaScript downloaded and so this website may not work as expected. Please download the latest software or switch device to avoid further issues.

News > Attacks & Threats > Agentic AI Isn't Risky; the Way Orgs Deploy It Is

Agentic AI Isn't Risky; the Way Orgs Deploy It Is

AI agents aren't black boxes — they're models interacting with software tools. The risk lies in their overlap.

In the mad dash to deploy agentic artificial intelligence (AI) technology, developers aren't taking enough time to understand how their programs work, and they're inadvertently generating a whole lot of very old-fashioned vulnerabilities.

The universe of AI agents in the advanced economies of today's world is immeasurably large; literally, nobody has any clue how many of these things are out there. Some recent data suggests that somewhere around a third of organizations have either already adopted or will adopt, agentic AI tech soon, but even those measurements rest on self-reporting and generalized data, or loose predictions. More here

Similar Stories

SharePoint access often means access to the keys of the kingdom, something attackers and defenders understand all too well. More...

A security researcher discovered the API keys can still be used for up to 23 minutes after deletion, even though the clo… More...

GitHub confirmed a data breach this week involving the theft of thousands of developer code repositories. One threat act… More...

Microsoft has disclosed a new security vulnerability impacting on-premise versions of Exchange Server that it said has c… More...

A Nitrogen ransomware attack on Foxconn's North American facilities is one of 600 hits on manufacturers this year, as ga… More...

Have your say

 

News Categories

AI agents aren't black boxes — they're models interacting with software tools. The risk lies in their overlap. More...

Four talks tracing the path from Principles to Practice in Trustworthy AI. More...

SharePoint access often means access to the keys of the kingdom, something attackers and defenders understand all too we… More...

Join our multi-language webinar on June 11, 2026 to hone your cybersecurity skills, expand your practical knowledge and … More...

A security researcher discovered the API keys can still be used for up to 23 minutes after deletion, even though the clo… More...

image

Contact Us

Security Interest Group Switzerland
c/o Bridge Head AG
Sulzbergstrasse 34
5430 Wettingen
Switzerland

Follow Us

This website is powered by
ToucanTech