Securing Code in the Age of AI
summary
AI-augmented development speeds feature delivery but multiplies risk: the talk shows a live demo wiring GitHub Copilot instructions, custom agents, and skills to run open-source scanners (Bandit, CodeQL) and produce actionable reports and Copilot Autofix pull requests. It cites 39 million secrets leaked on GitHub as a surprising data point, explains push protection, dependency review, code scanning and AutoFix flows, and presents a custom security agent that detects injection, hardcoded tokens and supply‑chain gaps and refuses to execute analyzed code.
AI-written summary · about
chapters (15)
- 0:00Introduction and agenda
- 1:39The AI coding revolution
- 5:10Threat landscape overview
- 7:27Anatomy of an application
- 8:12Managing exposed secrets
- 10:03Prevention and detection
- 12:29GitHub secret protection
- 15:00Push protection features
- 16:52Dependency and code scanning
- 23:42Guardrails and strategies
- 29:10Secure code generation
- 30:59Secure custom AI agents
- 32:55Demo: Custom security agents
- 45:03Advanced security scanning
- 56:13Conclusion and takeaways
related talks
41mCode Security Reinvented Navigating the era of AI
30mHuman vs AI: How to Ship Secure Code
38mCode Security Reinvented: Navigating the era of AI
26mSmarter Code, Sneakier Risks: Supply Chain Security in the Age of AI
32mCode Security Reinvented: Navigating the Era of AI
30mWhat Are the Security Risks Associated with AI-Generated Code? 🤔
01h 02mHow AI is impacting cybersecurity. Does it?
48mAI Impact on Cybersecurity and Privacy