AI-generated code introduces 15 vulnerabilities on average per codebase, but the actual risk depends on framework pairing more than the model used.
Researchers escaped the sandboxes in Cursor, Codex, Gemini CLI and Antigravity by having the AI agent write files that trusted host tools later run. Multiple CVEs, patches, and Google downgrading two Antigravity findings. […]
Marc Maiffret reflects on Code Red’s legacy and the security lessons helping organizations navigate AI risk today.
Attackers have begun exploiting a critical vulnerability (CVE-2026-6875) in the ServiceNow AI Platform, according to threat intelligence company Defused. […]
7-Zip version 26.02 was released to fix a remote code execution vulnerability that could allow attackers to execute malicious code by convincing users to open specially crafted compressed files. […]
Public exploits have been released for the critical „wp2shell“ remote code execution vulnerabilities affecting WordPress Core, making it imperative that administrators patch their sites immediately. […]