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

Microsoft seized 50 websites and disabled more than 150 domains as part of a coordinated disruption effort against a phishing-as-a-service platform targeting Microsoft 365 accounts… More...

A process parameter-poisoning technique evades EDR by injecting code into process initialization structures without usin… More...

MFA is essential, but it cannot replace OAuth governance, least-privilege scopes, consent monitoring, and rapid revocati… More...

Threat actors behind the "Phantom Deal" campaign are studying companies in extreme detail, aiming to dupe midlevel emplo… More...

The "Spring Ring" operation aims to compromise users of the collaboration suite to remotely access their sessions, sprea… More...

Have your say

 

News Categories

Microsoft seized 50 websites and disabled more than 150 domains as part of a coordinated disruption effort against a phishing-as-a-service platform targeting Microsoft 365 accounts… More...

A process parameter-poisoning technique evades EDR by injecting code into process initialization structures without usin… More...

MFA is essential, but it cannot replace OAuth governance, least-privilege scopes, consent monitoring, and rapid revocati… More...

You can't make an omelet without breaking a few eggs, and you can't patch nearly 1,000 CVEs without a few glitches. More...

Threat actors behind the "Phantom Deal" campaign are studying companies in extreme detail, aiming to dupe midlevel emplo… 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