Episode 126: Hacking AI Series: Vulnus ex Machina - Part 3

Episode 126: In this episode of Critical Thinking - Bug Bounty Podcast we wrap up Rez0’s AI miniseries ‘Vulnus Ex Machina’. Part 3 includes a showcase of AI Vulns that Rez0 himself has found, and how much they paid out.
Follow us on twitter at: x.com/ctbbpodcast
Got any ideas and suggestions? Feel free to send us any feedback here: info@criticalthinkingpodcast.io
Shoutout toYTCracker (twitter.com/realytcracker) for the awesome intro music!
====== Links ======
Follow your hosts Rhynorater and Rez0 on Twitter:
x.com/Rhynorater
x.com/rez0__
====== Ways to Support CTBBPodcast ======
Hop on the CTBB Discord at 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.
You can also find some hacker swag at ctbb.show/merch!
Today’s Sponsor - ThreatLocker Web Control
criticalthinkingpodcast.io/tl-webcontrol
====== Resources ======
Claude Code System Prompt (x.com/wunderwuzzi23/status/1926867263451169116)
Attacking AI Agents (x.com/wunderwuzzi23/status/1926430567479857460)
Probability of Hacks (sensecurity.io/probability-of-hacks)
New Gemini for Workspace Vulnerability Enabling Phishing & Content Manipulation (hiddenlayer.com/innovation-hub/new-gemini-for-…)
How to Hack AI Agents and Applications (josephthacker.com/hacking/2025/02/25/how-to-ha…)
====== Timestamps ======
(00:00:00) Introduction
(00:02:53) NahamCon Recap, Claude news, and wunderwuzzi writeups
(00:08:57) Probability of Hacks
(00:11:27) First AI Vulnerabilities
(00:18:57) AI Vulns on Google
(00:25:11) Invisible prompt Injection