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

Threat Actors Use AI Agents and Cursor IDE to Automate Active Directory Attacks and Beat EDR

4 June 2026  |  dark6  |  Cybercrime

Sophos has uncovered a Russian-speaking threat actor using AI-assisted tools, Cobalt Strike, and a purpose-built automated lab to develop EDR bypass malware targeting Active Directory environments — with...

>> read more

Five OpenClaw Zero-Days Let Attackers Silently Hijack AI Agent Access on Slack, Teams, and Discord

4 June 2026  |  dark6  |  Vulnerability

Researcher Philip Garabandic disclosed five zero-day vulnerabilities in OpenClaw allowing identity spoofing to hijack trusted AI agent access across Slack, Discord, Microsoft Teams, Matrix, and Zalo. The same...

>> read more

Meta AI Flaw Lets Attackers Hijack Instagram Accounts Without Verification — Premium Handles Worth $1M+ Stolen

1 June 2026  |  dark6  |  AI

A critical flaw in Meta's AI account recovery tool allowed attackers to trick the chatbot into sending password reset codes with no identity verification, enabling theft of premium...

>> read more

BadHost (CVE-2026-48710): Critical Authentication Bypass Threatens Thousands of AI Agent Applications

28 May 2026  |  dark6  |  Vulnerability

A newly disclosed critical vulnerability dubbed 'BadHost' (CVE-2026-48710) enables attackers to bypass authentication in FastAPI and Starlette-based AI applications through manipulated HTTP Host headers. Thousands of LLM inference...

>> read more

AI Discovers 10,000+ Zero-Days: Anthropic’s Claude Mythos Preview Transforms Cybersecurity Defense

24 May 2026  |  dark6  |  AI

Anthropic's Claude Mythos Preview AI model has autonomously discovered over 10,000 critical zero-day vulnerabilities across major software systems as part of Project Glasswing, revealing both the extraordinary potential...

>> read more

Claude Code’s Five-Month Network Sandbox Bypass Silently Exposed Developer Credentials and Source Code

21 May 2026  |  dark6  |  Vulnerability

Anthropic's Claude Code harbored a critical SOCKS5 null-byte injection sandbox bypass for over five months, allowing attackers to silently exfiltrate developer credentials, source code, and API keys. The...

>> read more

First Public macOS Kernel Exploit on Apple M5 Bypasses Hardware Memory Protection — Developed in Just Five Days With AI Assistance

18 May 2026  |  dark6  |  Vulnerability

Security researchers have developed the first known public macOS kernel exploit targeting Apple M5 hardware, bypassing Memory Integrity Enforcement (MIE) — a protection Apple spent five years building....

>> read more