#128 Robiin: Cloudflare’s AI Security Skill Found 6/6 Bugs - Claude Code Caught 4
Got something to say to this podcast? Send a voicemail, and you might hear yourself on the next episode!
AI coding agents can build working apps fast, but they can also miss basic security mistakes. I tested 4 security approaches on an app with 6 deliberate vulnerabilities — and the results were surprisingly different.
We’ll talk about:
Cloudflare Security Skill: It found all 6 planted bugs, though several still needed independent validation.
Claude Code Security Review: /security-review caught 4/6, especially logic bugs like broken access control and data leaks.
One Simple AI Prompt: A…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.