Theori built 28 apps with AI coding agents and scanned each one through its pentesting platform. Five models did the building, split between Anthropic and OpenAI, across apps written from a spec, thrown together from a casual prompt, and rewritten from an aging PHP codebase. The team went in expecting injection everywhere. SQL injection, cross-site scripting, the bugs that fill security tutorials. Those barely showed up. The models reached for prepared statements and ORMs on … More
The post The AI code vulnerabilities that grow with your app appeared first on Help Net Security.
source & further reading
helpnetsecurity.com — original article
OpenAI: Our models breached Hugging Face during a cyber capability test
OpenAI Presence connects AI agents to enterprise data with built-in guardrails
Astelia extends reachability analysis with agentic AI for vulnerability management