2026-07-21
BleepingComputer
5 related
Researchers found sandbox escapes or boundary bypasses in Cursor, Codex, Gemini CLI, and Antigravity by writing files that trusted tools use; most are patched
Security researchers broke out of the sandboxes in four widely used AI coding agents, including Cursor, OpenAI's Codex …
2026-06-30
The Information
4 related
Internal documents: Meta is placing strict limits on how engineers in its applied AI division can use Claude Code and Codex, fearing inadvertent distillation
2026-06-29
The Information
10 related
Internal documents: Meta is placing strict limits on how engineers in its applied AI division can use Claude Code and Codex, fearing inadvertent distillation
2026-04-29
Wired
5 related
OpenAI's instructions in Codex CLI contain a line, repeated several times, that forbids the tool from randomly mentioning goblins, gremlins, and other creatures
“Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely …
2025-10-22
Simon Willison's Weblog
8 related
First impressions of ChatGPT Atlas, as browser agents remain confusing, with insurmountable security and privacy risks including prompt injection attacks
a web browser with ChatGPT built in, not bolted on. The browser is the agent now. Tabs are prompts. The search bar is dead. Welcome to the post-URL era. P.S the browser wrote this on its own Arlan / @...
Loading articles...