Attention: You are using an outdated browser, device or you do not have the latest version of JavaScript downloaded and so this website may not work as expected. Please download the latest software or switch device to avoid further issues.
| 14 May 2026 | |
| Written by Gabi Gerber | |
| Attacks & Threats |
Developers using the latest versions of AI coding tools like Claude Code, Cursor CLI, Gemini CLI, and CoPilot CLI could inadvertently execute malicious code on their systems with a single keypress, or no keypress at all in continuous integration environments.
That, according to researchers at Adversa AI, is because none adequately warn users of how a malicious repo can auto-approve and spawn a Model Context Protocol (MCP) server without their explicit approval or knowledge. All four coding tools show some form of a trust dialog prompting the user to indicate whether they trust a particular repo, but they do not offer full details on what that consent might actually entail.
Adversa AI identified Claude Code as offering the least information in its trust dialog, and Gemini AI as offering the most, along with a choice in terms of allowing or disallowing an MCP server to execute on the developer's system. But the exposure is the same in all four, according to Adversa's lead researcher, Rony Utevsky. More here
Threat actors behind the "Phantom Deal" campaign are studying companies in extreme detail, aiming to dupe midlevel employees into initiating large financial transfers. More...
The "Spring Ring" operation aims to compromise users of the collaboration suite to remotely access their sessions, sprea… More...
Microsoft has disclosed details of a new ClickFix variant, dubbed TerminalFix, that aims to trick users into running a m… More...
OpenAI's Hugging Face attack postmortem shows agents don't care about rules — they need strong controls. More...
An untold number of ZBT routers sold around the world as white-label products come with several implants built by the ma… More...
Threat actors behind the "Phantom Deal" campaign are studying companies in extreme detail, aiming to dupe midlevel employees into initiating large financial transfers. More...
The "Spring Ring" operation aims to compromise users of the collaboration suite to remotely access their sessions, sprea… More...
Microsoft has disclosed details of a new ClickFix variant, dubbed TerminalFix, that aims to trick users into running a m… More...
OpenAI's Hugging Face attack postmortem shows agents don't care about rules — they need strong controls. More...
An untold number of ZBT routers sold around the world as white-label products come with several implants built by the ma… More...
