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

Researchers escaped the sandboxes of Cursor, Codex, Gemini CLI and Antigravity without breaking them. Three vendors patched; Google downgraded its two.

Researchers exposed seven sandbox escapes in Cursor, Codex, Gemini CLI & Antigravity. Discover how AI coding agents ...

An exposed attack server led Lexfo to three Microsoft 365 phishing operations using Evilginx and device code abuse to capture sessions.

Discover how the Rogue Agent vulnerability in Google Dialogflow CX enabled persistent AI agent compromise, data exfiltration, ...

By manipulating files later consumed by trusted software, coding assistants can effectively cross security boundaries while ...

The JadePuffer autonomous AI agent has upgraded with custom malware called EncForge that focuses on encrypting AI assets, ...

Kiwoom Securities announced on July 21 that it has released a REST API-based domestic stock CLI (Command Line Interface) and sample code in collaborat ...

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

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

The agentic operator documented as the first ransomware campaign run end-to-end by a large language model (LLM) has returned ...

When the generative AI boom sparked into life in late 2022, business executives and team leaders from across the world were captivated by its potential. Many business leaders quickly recognized the ...