An agentic coding tool tasked with cloning and setting up a seemingly benign GitHub repository could execute a malicious ...

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

A China-linked threat cluster has been exploiting vulnerable Roundcube servers at U.S. and Canadian universities to steal ...

In the brief history of AI security, the prompt injection has quickly become the top threat. Large language models are ...

GitHub's npm package manager will ship its most significant security redesign in years this July, when npm v12 makes three long-automatic install behaviors require ...

Kaspersky says 90+ spoofed domains use malicious installers and SEO to deliver AsyncRAT to Windows systems through ScreenConnect.

Mozilla’s 0din team showed how a Claude Code malware GitHub repo attack could use a clean-looking repository to open a ...

An exposed WP-SHELLSTORM server revealed tools, logs, cloud credentials, and thousands of webshells used in a large website ...

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

Researchers at the AI Now Institute developed a proof-of-concept exploit showing common AI tools used for security could ...

SCMBANKER watches banking windows, captures screenshots, hijacks CLABE and card numbers, and can deploy Remote Utilities for ...