Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
is a new AI research framework for building open-ended, generally capable embodied agents. MineDojo features a massive simulation suite built on Minecraft with 1000s of diverse tasks, and provides ...
GameCraft-Bench evaluates whether coding agents can transform natural-language game specifications into complete, playable Godot projects. Unlike traditional coding tasks, game generation depends on ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results