Malicious AI browser extensions collected LLM chat histories and browsing data from platforms such as ChatGPT and DeepSeek.
All the nation-state hackers are vibe coding. Vibeware won't win any coding awards. It's not pretty. It doesn't target any ...
Source Code Exfiltration in Google AntigravityTL;DR: We explored a known issue in Google Antigravity where attackers can silently exfiltrate proprietary source codeBy hiding malicious instructions ...
OAuth redirection is being repurposed as a phishing delivery path. Trusted authentication flows are weaponized to move users ...
A threat actor has weaponized Anthropic’s Claude Code to breach the Mexican government’s systems and steal over 150GB of data ...
Claude Code is the new AI coding assistant that many users are using in their workflows. Here's everything you need to know ...
Chainguard, the trusted source for open source, today announced it has expanded Chainguard Libraries coverage across Python, Java, and JavaScript, with customers seeing 94% coverage across the Python ...
In an open letter to Google and the Android developer community, Keep Android Open argues that the new policy threatens ...
The Arkanix Stealer malware can collect and exfiltrate system information, browser data, VPN information, and arbitrary files ...
Researchers warn malicious packages can harvest secrets, weaponize CI systems, and spread across projects while carrying a ...
Sample files for Azul are kept in a Simple Storage Service (S3) compatible binary large object (blob) store, and processed ...
A Russian hacker was recently seen brute-forcing their way into hundreds of firewalls - but what makes this campaign really stand out is the fact that the seemingly low-skilled threat actor was able ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results