meta_pixel
Tapesearch Logo
Log in
CyberWire Daily

When AI gets a to-do list. [Research Saturday]

CyberWire Daily

N2K Networks, Inc.

Daily News, Tech News, News, Technology

4.61K Ratings

🗓️ 3 May 2025

⏱️ 21 minutes

🧾️ Download transcript

Summary

This week, we are joined by ⁠Shaked Reiner⁠, Security Principal Security Researcher at ⁠CyberArk⁠, who is discussing their research on"Agents Under Attack: Threat Modeling Agentic AI." Agentic AI empowers LLMs to take autonomous actions, like browsing the web or executing code, making them more useful—but also more dangerous. Threats like prompt injections and stolen API keys can turn agents into attack vectors. Shaked Reiner explains how treating agent outputs like untrusted code and applying traditional security principles can help keep them in check. The research can be found here: ⁠Agents Under Attack: Threat Modeling Agentic AI Learn more about your ad choices. Visit megaphone.fm/adchoices

Transcript

Click on a timestamp to play from that location

0:00.0

You're listening to the Cyberwire Network, powered by N2K.

0:11.4

And now a word from our sponsor, Black Kite.

0:15.1

If third-party risk is keeping you up at night, you're not alone.

0:18.7

It's a constant battle.

0:20.5

Black Kite's third-party

0:21.6

cyber risk platform is built on real-world threat intelligence, straight from their research

0:26.8

team's ongoing breach analysis, dark web monitoring, and attacker tactics. That means you get a

0:33.1

hacker's eye view of your supply chain to proactively spot risks. And speaking of research, they just dropped

0:39.6

their 2025 third-party breach report, breaking down last year's biggest trends and what's coming next.

0:46.5

Grab the report now at www.com.com.

1:09.1

Hello, everyone, and welcome to the Cyberwires Research Saturday.

1:14.2

I'm Dave Bittner, and this is our weekly conversation with researchers and analysts tracking down the threats and vulnerabilities, solving some of the hard problems and protecting ourselves in our rapidly evolving cyberspace.

1:22.8

Thanks for joining us.

1:33.3

So, EGNTKica is kind of a concept, I should say. And it basically means any type of system, any type of code that uses LLM in a sort of way that allows

1:42.3

the LLM to decide about the control flow of the program.

1:48.3

That's Chakhead Rayner, principal security researcher at CyberArk.

1:53.2

Discussing their research, agents under attack, threat modeling agentic AI.

1:58.8

We'll have a link in the show notes.

2:07.9

Thank you. modeling Agenic AI. We'll have a link in the show notes. What initially prompted you and your colleagues to investigate the security implications

2:13.1

of Agenic AI?

2:15.4

Yeah, so as I'm sure we all know, the buzz around Agentic AI is very much present in our industry

2:23.9

in the last couple of months.

...

Please login to see the full transcript.

Disclaimer: The podcast and artwork embedded on this page are from N2K Networks, Inc., and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of N2K Networks, Inc. and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.

Copyright © Tapesearch 2025.