Opening a repository can run its code inside seven AI coding agents.
Security researchers disclosed a flaw class on 1 September that hits seven AI coding agents. The code runs before the tool asks for approval, and sometimes before you even sign in. Codex, Cursor and Goose shipped fixes, but three agents and one Claude Code path stayed open.
Why it mattersIf you let an AI agent open code you did not write, that code can run first. The weak point was not the model but the ordinary tools the agent quietly runs around it.
Read in the app — free, in 9 languages
Related stories
OpenAI says it hit its own deadline for an AI research intern.2026-09-07Google put full song generation into the Gemini app for everyone.
2026-09-06A startup now sells hosted AI models with the safety stripped out.
2026-09-06Rangers rescued three hikers who packed what Gemini told them to.
2026-09-06Nvidia's free tool turns the computers in your home into one cluster.
2026-09-06