L0pht Hacker Chris Wysopal on Securing AI-Written Code: 'Make It Secure' Isn't a Prompt
WeldPond · x · 2026-10-07
Veracode Chief Security Evangelist Chris Wysopal, an original L0pht vulnerability researcher, discusses how AI makes sophisticated attacks cheaper and faster while arguing defenders adopting the same tools prevents a cyber doomsday. The podcast covers prompt injection in agents and MCPs, zero trust, security debt in SaaS acquisitions, and a practical 'secure on first write' checklist: memory-safe languages, package firewalls, AI-assisted static analysis with context, and explicit security intent for coding agents.
More from coding & agent
- Flipper harness routes 64% of tasks to DeepSeek, cutting API bill by over 60% — toptickcrypto · 2026-10-07
- Overmind: Open Platform That Turns Production Traces Into Fine-Tuning Data for Agents — cneuralnetwork · 2026-10-07
- Ampersand launches integration infrastructure powering AI agents in Salesforce, SAP and NetSuite — SimplyAnnisa · 2026-10-07
- Armature launches agent.reviews with 100k+ tool reviews written by AI agents — ycombinator · 2026-10-07
- How Ampersand works: YAML-defined integrations, MCP server, free tier for 5 production customers — testingcatalog · 2026-10-07
- LangChain's model router cut coding agent costs 64% without quality loss — LangChain · 2026-10-07