OpenScience is an AI workbench for scientific research. You give it a goal, and it works through the research loop the way a ...

Fake CVE exploit repos pull frint and skytext packages to steal researcher credentials, with servers still live as of July 1.

Multiple weaponized proof-of-concept (PoC) exploits on GitHub delivered a Python-based remote access trojan (RAT) called ChocoPoC that can execute commands and steal sensitive data. However, ChocoPoC ...

Mozilla 0DIN’s Claude Code demo shows how clean GitHub repos can expose AI coding agents to prompt injection, reverse shells, ...

A campaign active since last November has been targeting Python developers building Telegram bots with trojanized Pyrogram ...

Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.

Three levels of indirection, all with seemingly innocuous steps, will catch a bot off-guard.

Connect all your configuration files and autogenerate code—Jsonnet is the missing piece for large code bases.

Reference implementation for Continual Harness (Karten et al., 2026), a reset-free framework that automates agentic-harness refinement through online in-context learning, evaluated on Pokémon Red and ...