Secure Bulletin Navigating the cyber sea with knowledge
Home > Tag > AI vulnerability
#AI vulnerability

Researcher Chains a Guardrail Bypass With a Path Traversal Flaw to Access System Files in ChatGPT

4 July 2026  |  dark6  |  Vulnerability

A proof-of-concept disclosed by researcher zer0dac combined social engineering against ChatGPT's own safety logic with a path traversal bug to retrieve restricted system files through the platform's file...

>> read more

DuneSlide: Critical Zero-Click RCE Bugs in Cursor IDE Put Fortune 500 Developer Machines at Risk

2 July 2026  |  dark6  |  Vulnerability

Two critical zero-click RCE vulnerabilities (CVE-2026-50548, CVE-2026-50549) in Cursor IDE, dubbed DuneSlide, allow attackers to escape the AI coding agent sandbox via prompt injection with no user interaction...

>> read more

SiderAI and MaxAI Chrome Extensions Expose 10 Million Users to Full Browser Compromise

22 June 2026  |  dark6  |  Vulnerability

Critical vulnerabilities dubbed Spyder and MaXSS have been discovered in the SiderAI and MaxAI Chrome extensions, which together are installed on over 10 million devices. The flaws allow...

>> read more

Google Gemini Voice Assistant Hijacked via WhatsApp, Slack and SMS: Researchers Bypass All Google Defenses

5 June 2026  |  dark6  |  Vulnerability

SafeBreach researchers demonstrate how attackers can silently hijack Google Gemini through malicious payloads in WhatsApp, Slack, SMS, and other messaging app notifications, bypassing all of Google patched defenses...

>> read more