About this episode
The episode features a discussion with Ari Marzuk about vulnerabilities in AI coding tools and the implications of AI-driven development.
In this episode of Resilient Cyber, we will be sat down with Ari Marzuk, the researcher who published "IDEsaster", A Novel Vulnerability Class in AI IDE's. We will be discussing the rise of AI-driven development and modern AI coding assistants, tools and agents, and how Ari discovered 30+ vulnerabilities impacting some of the most widely used AI coding tools and the broader risks around AI coding. Ari's background in offensive security — Ari has spent the past decade in offensive security, i...
People in this episode
Host: Chris Hughes
Guest: Ari Marzuk
Topics covered
- AI-driven development
- AI coding assistants
- vulnerabilities in AI tools
- offensive security
- risks of AI coding
Keywords
- AI IDEs
- vulnerabilities
- coding assistants
- offensive security
- AI tools
Mentioned in this episode
Books & works: IDEsaster
More episodes of Resilient Cyber
- AI Is Winning the Cyber Arms Race · June 3, 2026 · 36 min
- Securing the Agentic SDLC · May 29, 2026 · 49 min
- The Agentic GRC Revolution · May 19, 2026 · 32 min
- Identity as Infrastructure in the Agentic Era · May 13, 2026 · 34 min
- Why AI Security Feels So Fragile · May 1, 2026 · 23 min
- You Can't Trust What You Can't Verify — The Case for AI Model Identity · April 28, 2026 · 1 min
Explore listener stats, chart rankings, contacts and more on the Resilient Cyber podcast page.