Source Code Exfiltration in Google Antigravity‍TL;DR: We explored a known issue in Google Antigravity where attackers can ...

UNC4899 breached a crypto firm via AirDrop malware and cloud exploitation in 2025, stealing millions through Kubernetes and Cloud SQL abuse.

BlackBox AI, a popular VS Code coding assistant, has a critical indirect prompt injection vulnerability. Hackers can exploit this to gain remote root access to a user’s computer.

Learn how to detect anomalous context injections in MCP deployments using post-quantum cryptography and ai-driven behavioral analysis to prevent puppet attacks.

Safe coding is a collection of software design practices and patterns that allow for cost-effectively achieving a high degree ...

Discover OpenFang, the Rust-based Agent Operating System that redefines autonomous AI. Learn how its sandboxed architecture, pre-built "Hands," and security-first design outperform traditional Python ...

The module targets Claude Code, Claude Desktop, Cursor, Microsoft Visual Studio Code (VS Code) Continue, and Windsurf. It also harvests API keys for nine large language models (LLM) providers: ...

Are AGENTS.md files actually helping your AI coding agents, or are they making them stupider? We dive into new research from ETH Zurich, real-world experiments, and security risks to find the truth ...

Adaptable robotic systems incorporating AI, new vision tech and low-code programming are being used to tackle frequent ...

These new models are specially trained to recognize when an LLM is potentially going off the rails. If they don’t like how an interaction is going, they have the power to stop it. Of course, every ...

Group-IB links poisoned mobile banking apps to GoldFactory Attackers decompile legitimate apps, add trojans/backdoors, and spread them via phishing lures and fake sites Advanced malware families ...