A trio of bug hunters researching frontier AI labs’ security weaknesses chained two vulnerabilities to take over multiple OpenAI employees’ ChatGPT accounts, then used that access to demonstrate they ...

By exploiting how AI coding agents retrieve and verify plugins, researchers were able to execute malicious code even when the agent was told to use a trusted, approved version.

To demonstrate the access without reading any internal code, Hacktron says it took over an OpenAI employee’s account whose Codex integration was linked to OpenAI’s GitHub organization, then used it to ...

Following former Maine Sen. George Mitchell’s Feb. 5 resignation as honorary chair of the Mitchell Institute, organizations have begun removing his name from various programs after he was mentioned ...

Researchers used Anthropic’s Claude Opus 5 to help weaponize an image-decoder vulnerability, compromise OpenAI’s community forum, take over employees’ ChatGPT and Codex accounts, and reach an internal ...