Tanya Janca - Secure Vibe Coding

If AI writes all the code and the developer barely reads it, where does AppSec fit? Tanya Janca returns to define vibe coding and explain why models trained on insecure public code do not understand secure design by default. She and the hosts build a practical secure-vibe-coding framework: explicit requirements, human-led threat modeling, reusable security prompts, iterative review, SAST, and independent testing. Tanya shares hard-earned examples of Claude removing error handling, models confidently reviewing their own insecure output, and developers accepting enormous finding backlogs for code they did not enjoy writing. The discussion also examines whether security tooling will consolidate into AI platforms, how AppSec must be reimagined, and why continuous, embedded guidance matters more than occasional training. Tanya closes by introducing her DevSecStation podcast.Connect with Tanya Janca:→ Tanya Janca on LinkedIn→ SecureMyVibe→ DevSecStationMentioned in this episode:→ SecureMyVibe→ OWASP Top 10→ Burp Suite→ OWASP ZAP→ DevSecStation→ Tanya Janca (SheHacksPurple)→ ChatGPT→ Stack Overflow→ The Security Table podcastFollow the Application Security Podcast:➜ Home➜ X➜ LinkedIn➜ YouTube➜ Instagram➜ FacebookChapters:00:00 Tanya Janca returns02:10 What vibe coding actually means04:03 AI adoption and how developers prompt05:57 Treating AI like an intern07:28 Do AI systems need parental controls?09:34 Security prompts for everyday development11:47 Models, memory, and protecting sensitive data14:11 What happens when Claude goes away?16:02 The most dangerous vibe-coding misconception18:06 Threat modeling before AI writes the code22:48 Using AI throughout the development lifecycle25:32 A reusable secure-prompt framework29:09 Expose security assumptions and challenge flattery32:30 Reviewing an AI-generated codebase36:09 Will AI platforms absorb security tooling?37:39 Five million findings for code nobody wrote42:19 The remaining pieces of secure vibe coding43:52 Reimagining AppSec45:25 Continuous guidance beats occasional training46:05 Introducing DevSecStation47:12 Closing thoughts