Varonis AI Threat Lead on Copilot Exploits, Prompt Injection, and the AI Hacking Trifecta
The host interviews Mark Vaitsman, AI threat research lead at Varonis, about Varonis Threat Labs' research into AI vulnerabilities, including a chain of single-click exploits in Microsoft Copilot (including "CoSnitch") and an Atlassian Confluence issue dubbed "RovoBlast" involving prompt injection, bypassing guardrails, and data exfiltration via a web-capable subagent.
Vaitsman explains why built-in model guardrails are insufficient, citing AI's lack of loyalty and "unlimited hunger for data," and argues for layered controls like least privilege, monitoring, and restricting data access.
He discusses psychological guardrail bypasses, introduces an "AI Hacking Trifecta" framework—enter, evade, escape—and comments on research showing AI-generated patches often fail, emphasizing human-led validation and guidance when using AI tools for security research.
00:00 Weekend Show Kickoff 00:44 Meet Mark Vaitsman 03:38 Teaching the Next Gen 04:19 Copilot Exploit Code Snitch 06:04 Atlassian RoboBlast Breakdown 08:52 Why Guardrails Fail 13:15 Manipulating Models to Comply 17:06 Securing Agents Without Handcuffs 20:11 AI Hacking Trifecta Framework 23:43 AI Patches and Human Research 27:43 Hope and Closing Thoughts
Podden och tillhörande omslagsbild på den här sidan tillhör
David Shipley. Innehållet i podden är skapat av David Shipley och inte av,
eller tillsammans med, Poddtoppen.
