Researchers have discovered two vulnerabilities in the widely used Cursor AI-enabled integrated development environment (IDE) ...

SentinelOne says macOS.Gaslight uses prompt injection to mislead AI-based malware analysis, steal data, and use Telegram for ...

Security tooling is not written in a single language. Python powers most automation. C sits at the exploit layer. PowerShell ...

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

The safety check that is supposed to stop an AI coding agent from running a dangerous command can be walked straight past using a shell trick that has been public for decades. New research from ...

OpenAI brought Codex Remote to general availability on June 25, 2026, opening phone-based control of long-running AI coding sessions to every paid ChatGPT subscriber — Plus, Pro, Business, Enterprise, ...

A developer reverse-engineering Anthropic's Claude Code binary discovered on June 30, 2026, that the tool had been silently encoding hidden signals into its AI system prompts for at least three months ...

A new piece of malware tries to trick AI-assisted analysis into showing errors.

International nanoscientists publish a new blueprint reframing the protein corona as a programmable navigation interface to cross the blood-brain barrier.

Two new Cursor IDE vulnerabilities let an attacker break out of the editor’s command sandbox. All it takes is text the AI agent reads on your behalf. Cato AI Labs disclosed the pair, tracked as ...