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 ...

Cybersecurity researchers have uncovered two hijacked npm packages and a cluster of Go packages that are designed to deploy a Python-based information stealer on compromised Windows, Linux, and macOS ...

JFrog says six malicious npm packages used hidden install-time execution, JSONKeeper fetches, and sandbox checks to enable remote access.

The goal in this project is to provide a simple Unix-like terminal on iOS. It uses ios_system for command interpretation, and includes all commands from the ios_system ecosystem (nslookup, whois, ...

Mozilla researchers revealed a new attack that tricks Claude Code into running hidden commands from seemingly harmless GitHub repositories.

There was an error while loading. Please reload this page.

A North Korea-linked macOS backdoor has been caught hiding a prompt injection that targets malware analyst's AI tools, rather ...

Claude Code has a non-interactive mode called claude -p (short for claude --print) that you can call with a single command instead of using the chat interface. This is quietly useful, and I think ...