An Honest Conversation About AI Security

About this episode

The episode features a discussion on the vulnerabilities of AI security with expert Katherine McNamara.

Send us Fan Mail Ready for a reality check on AI security? We invited Cisco cybersecurity expert Katherine McNamara to dig into where large language models actually break: from prompt injection and over-permissioned plugins to reckless “vibe-coded” apps that leak IDs, photos, and entire backends. The stories are real, the stakes are high, and the fixes are concrete. We trace how AI sprawl mirrors the worst of early IoT—weak defaults, poor isolation, and a stampede to integrate models into bil...

People in this episode

Guest: Katherine McNamara

Topics covered

• AI security
• cybersecurity
• large language models
• prompt injection
• technology integration

Keywords

• AI security
• cybersecurity
• large language models
• prompt injection
• technology risks

Mentioned in this episode

Organizations: Cisco

More episodes of Cables2Clouds

• We Doomscroll So You Don’t Have To - Monthly News Update · May 20, 2026 · 28 min
• Ethical Hacking Basics · May 6, 2026 · 41 min
• Can You Fly With Glass Wings? - Monthly News Update (with a Surprise) · April 22, 2026 · 43 min
• What is Spec-Driven Development? · April 8, 2026 · 39 min
• Please Don’t Dump Data Center Soup - Monthly News Update · March 25, 2026 · 32 min
• When AI Deletes Production: Guardrails, MCP Risks, And The Surveillance Creep · February 25, 2026 · 42 min