AI Security20 October 2026
Battle Drones: Treating a Vibe-Coded Game's Audio Link as Untrusted Input
Simon Willison's agent-built RTS syncs multiplayer state over sound between nearby devices. As a design, it is a small, useful case study in out-of-band channels, determinism and trusting AI-generated code.
vibe codingai-generated codeuntrusted input
3 min readRead
AI Security13 July 2026
AI Coding Agents Are Boosting Commit Velocity — And Security Debt With It
A viral GitHub commit-frequency chart shows how much modern coding agents accelerate output. Independent testing suggests the code behind that velocity still fails basic security checks at a striking rate.
ai-securityvibe-codingsecure-code-review
4 min readRead
DevSecOps28 June 2026
AI Writes the CI/CD Pipeline: Auditing AI-Generated GitHub Actions Workflows
Simon Willison's browser-compat-db used two AI models to generate a complete build pipeline — a sign of where development is heading and a prompt to ask whether security review has kept pace.
github-actionsdevsecopssupply-chain-security
4 min readRead