#prompt-injection
8 episodes
#3422: How Rival Labs Reverse-Engineer a New AI Model in Hours
Inside the organized frenzy when a closed-source model drops — and how competitors map its every weakness.
#2691: The Usability Tax of Least Privilege
Is it time to let AI agents handle your API key creation and rotation? We explore the real security tradeoffs.
#2472: When Guardrails Break: The Hidden Costs of AI Gateway Filtering
PII detection at the gateway layer can block legitimate invoices. Here's how guardrails actually work and where they fail.
#2180: The Sandboxing Tradeoff in Agent Design
AI agents need broad permissions to be useful—but every permission expands the attack surface. We map the real threat landscape and the isolation t...
#1957: Why AI Agents Think in Circles, Not Lines
Linear AI pipelines are brittle. Learn why loops, reflection, and state management are the new standard for reliable, autonomous agents.
#1217: The Missing Ring Zero: Why LLMs Can't Keep Secrets
Discover why AI models leak their secret instructions and how to defend your intellectual property using modern prompt hardening techniques.
#1070: The Agentic Secret Gap: Securing the AI Developer Workflow
AI agents write code in seconds, but manual secret management is a major bottleneck. Explore how to bridge the gap between speed and security.
#44: When AI Trusts Too Much: The Art of Prompt Injection
AI's Wild West: Battling prompt injection and poisoning. Discover how AI threats are shifting from sci-fi to insidious attacks on the models...