Researchers escaped the sandboxes in Cursor, Codex, Gemini CLI, and Antigravity by exploiting files trusted host tools run.

Microsoft's newly released Agent Framework Harness packages the loops, planning, memory, context management and safety controls that developers previously had to assemble around AI models themselves.

Russia’s Sandworm hacking group is using fake CAPTCHA prompts to infect Ukrainian devices with malware across ten-plus ...

In a new campaign, North Korean hacking group Famous Chollima targeted crypto professionals through ClickFix lures to deliver ...

JADEPUFFER exploits Langflow CVE-2025-3248 to deploy ENCFORGE ransomware against AI model weights, vector indexes, and ...

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 ...

ACR Stealer is targeting enterprises through ClickFix lures, PowerShell scripts, blockchain services, and malicious image ...

The Russian state-sponsored hacking group Sandworm is now using the ClickFix attack technique to infect organizations in ...

From late April 2026 to mid-June 2026, Microsoft Defender Experts observed increased ACR Stealer activity across customer ...

DoorDash is opening a limited beta of dd-cli, a command-line tool that lets developers and AI agents search stores, build ...

A Russian-speaking threat actor known as "bandcampro" used Google's open-source Gemini CLI AI tool as a hacking agent and to ...

Mozilla 0DIN’s Claude Code demo shows how clean GitHub repos can expose AI coding agents to prompt injection, reverse shells, and credential risk.