Cybersecurity Research | Breaking Cybersecurity News | The Hacker News

An AI coding assistant that refuses to answer a dangerous request in its chat box can answer it anyway if the same request is broken into small, ordinary-looking steps inside a code editor. That is the finding of a  new study of GitHub Copilot  by researchers Abhishek Kumar and Carsten Maple. The models they tested through Copilot, Claude from Anthropic, and Gemini from Google, refused almost every harmful request when asked directly. Reframed as steps in a normal coding task, they produced the harmful answers in all 816 of the study's workflow runs. What makes this different from a typical jailbreak: no one asks for the harmful thing directly, and the model is not tricked into running someone else's code. It writes the banned content itself, as a side effect of a coding task it was told to improve. How it works The researchers call the method workflow-level jailbreak construction . Instead of a single blunt prompt, they asked Copilot to build an everyday piece of s...

Last year, there were discussions about Google Code—a platform that lets developers host their projects—being exploited to distribute malware. Research by zScaler has identified yet another instance where this platform has been misused. According to the Google Code site: "Project Hosting on Google Code provides a free collaborative development environment for open source projects. Each project includes its own member controls, Subversion/Mercurial repository, issue tracker, wiki pages, and downloads section. Our hosting service is designed to be simple, fast, reliable, and scalable, enabling you to concentrate on your open source development." The concerning project contained over 50 executable files in its download section. These files, mainly executable and zipped ".rar" files, have been uploaded over the past month, indicating that an attacker is actively using this free service to disseminate malware. VirusTotal results for the first file revealed that only 8 ...