The Hugging Face incident was bigger and worse than previously thought, with approximately 700 agents collaborating on a sophisticated, multistage attack.
The Hugging Face incident was bigger and worse than previously thought, with approximately 700 agents collaborating on a sophisticated, multistage attack.
A likely Iran-backed actor targeted more than 30 community water systems in Minnesota in a sobering reminder of rising threats to US critical infrastructure.
Apple on Monday released security updates for iOS, macOS, and the Safari web browser to address over three dozen flaws, including four vulnerabilities in WebKit that were discovered using artificial intelligence (AI) tools like Anthropic Claude and OpenAI Codex Security. The WebKit vulnerabilities are listed below – CVE-2026-43707 – A memory corruption issue that could…
Cybersecurity researchers have disclosed details of a vulnerability in OpenAI ChatGPT that leverages the artificial intelligence (AI) assistant’s implicit trust in Markdown links and images to trigger prompt injections and open the door to phishing attacks. The technique has been codenamed ChatGPhish by Permiso Security. “The chatgpt.com response renderer trusts Markdown links and Markdown
Evidence suggests that some of the payloads and extensions may date as far back as April 2023.
When people ask us, “Aren’t all endpoint solutions the same these days?” — our answer is simple: No. They’re not.
The security company looks to tackle new authentication challenges that could lead to credential leakage, as enterprises increasingly leverage AI browser agents.