Episode 152: In this episode of Critical Thinking - Bug Bounty Podcast we’re joined by Sasi Levi from Noma Security to talk about AI and Agentic Security. We also talk about ForcedLeak, a Google Vertex Bug, and debate if Prompt Injection is a real Vuln.

Follow us on twitter at: https://x.com/ctbbpodcast

Got any ideas and suggestions? Feel free to send us any feedback here: [email protected]

Shoutout to YTCracker for the awesome intro music!

====== Links ======

Follow your hosts Rhynorater, rez0 and gr3pme on X:

https://x.com/Rhynorater

https://x.com/rez0__

https://x.com/gr3pme

====== Ways to Support CTBBPodcast ======

Hop on the CTBB Discord at https://ctbb.show/discord!

We also do Discord subs at $25, $10, and $5 - premium subscribers get access to private masterclasses, exploits, tools, scripts, un-redacted bug reports, etc.

CHeck out our New Christmas Swag at https://ctbb.show/merch!

Today's Sponsor: ThreatLocker. Check out ThreatLocker Elevation Control

https://ctbb.show/tl-ec

And Noma Security! https://noma.security/

Today’s Guest: https://x.com/sasi2103

====== This Week in Bug Bounty ======

Vercel Platform Protection

Dedicated HackerOne program for Vercel WAF

YesWeHack Open Source Programs

Android recon for Bug Bounty hunters

====== Resources ======

Sasi's Tweet from 2015

ForcedLeak: AI Agent risks exposed in Salesforce AgentForce

Is Prompt Injection a Vulnerability?

====== Timestamps ======

(00:00:00) Introduction

(00:09:16) Google Vertex AI Bug

(00:29:28) Sasi's Background and Bug Bounty Journey

(00:38:55) Resources for AI and Agentic Security Methodology

(00:50:34) ForcedLeak

(01:02:06) Is Prompt Injection a Vuln?