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
A leaked GitHub token underscores what most organizations get wrong: Treating secrets management as a tooling problem rather than an identity problem. More...
In addition to executing entirely in memory, the malware's infection chain incorporates other anti-analysis techniques d… More...
The disgruntled researcher released yet another PoC for a Windows Defender bug that allows for system takeover, showing … More...
“Ghost-Sender" is the result of a widespread misconfiguration, according to researchers, and evidence indicates it's bei… More...
AI worms, or "viruses with wings and brains," adapt to new environments, seek out vulnerabilities, and will likely strik… More...
A leaked GitHub token underscores what most organizations get wrong: Treating secrets management as a tooling problem rather than an identity problem. More...
In addition to executing entirely in memory, the malware's infection chain incorporates other anti-analysis techniques d… More...
The disgruntled researcher released yet another PoC for a Windows Defender bug that allows for system takeover, showing … More...
“Ghost-Sender" is the result of a widespread misconfiguration, according to researchers, and evidence indicates it's bei… More...
AI worms, or "viruses with wings and brains," adapt to new environments, seek out vulnerabilities, and will likely strik… More...
