Mozilla researchers revealed a new attack that tricks Claude Code into running hidden commands from seemingly harmless GitHub repositories.
Attackers can inject indirect prompts in normal-looking repositories to trick Claude Code into spawning a reverse shell.
Spam accounts overwhelmed my database. Claude found the weaknesses, Codex wrote the fixes, and I deployed a new defense.
Mozilla’s 0din team showed how a Claude Code malware GitHub repo attack could use a clean-looking repository to open a ...
An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...
The offices of Google are pictured in London on February 28, 2026. JUSTIN TALLIS/AFP via Getty Images Google released agents-cli on April 21, 2026, and it has shipped 13 updates in the 71 days since — ...
Claude Sonnet 5 is the most agentic Sonnet model yet, rivaling Opus 4.8 in performance at lower prices, Anthropic said.
A researcher found that using Anthropic’s Claude Opus 4.7, he could break into the website of Front Gate—used by every ...
Princeton’s CEO-Bench gave 14 AI models $1 million to run a simulated SaaS startup for 500 days. Most went bankrupt or lost ...
Master Claude's five core features in 20 minutes. Learn how to use Chat, Code, Cowork, Design, and Routines to automate tasks ...
Mozilla 0DIN’s Claude Code demo shows how clean GitHub repos can expose AI coding agents to prompt injection, reverse shells, and credential risk.
Anthropic's Claude Science is a workbench that gives scientists one environment to do computational research, saving them ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results