The DuneSlide vulnerabilities enable zero-click prompt injection attacks that escape Cursor's sandbox and execute arbitrary code on the underlying operating system.
Two new Cursor IDE vulnerabilities let an attacker break out of the editor’s command sandbox. All it takes is text the AI agent reads on your behalf. Cato AI Labs disclosed the pair, tracked as ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results