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
Those closest to executives must match their security postures because the weakest link in a family can become the entry point for attacks. More...
A bug in Claude Code Desktop's preview pane can allow adversaries to quietly steal credentials from developers, includin… More...
Don't buy the hype! AI has been dumbing down cyberattacks, and serious threat actors are barely touching it. More...
Organizations don't need better vulnerability scanners; they need to know who owns their assets and has the authority an… More...
Threat actors are now hiding payloads by using DNS TXT records and browser cache pre-fetching, making it tougher to spot… More...
Those closest to executives must match their security postures because the weakest link in a family can become the entry point for attacks. More...
A bug in Claude Code Desktop's preview pane can allow adversaries to quietly steal credentials from developers, includin… More...
Don't buy the hype! AI has been dumbing down cyberattacks, and serious threat actors are barely touching it. More...
Organizations don't need better vulnerability scanners; they need to know who owns their assets and has the authority an… More...
Threat actors are now hiding payloads by using DNS TXT records and browser cache pre-fetching, making it tougher to spot… More...
