Microsoft Windows Alert—Angry Hacker Drops 2 New Zero-Day Exploits

The latest Microsoft Patch Tuesday rollout featured no zero-days. However, an angry hacker has just dropped two new 0-day ...

Running Claude Code or Claude in Chrome? Here's the audit matrix for every blind spot your security stack misses

Four research teams found the same confused deputy failure in Claude across three surfaces in 48 hours. This audit matrix ...
The Hacker News

Ollama Out-of-Bounds Read Vulnerability Allows Remote Process Memory Leak

Critical out-of-bounds read in Ollama before 0.17.1 leaks process memory including API keys from over 300000 servers via ...

JDownloader site hacked to replace installers with Python RAT malware

The website for the popular JDownloader download manager was compromised earlier this week to distribute malicious Windows ...
The Next Web

The AI industry’s model and agent skill repositories are full of malware. The infrastructure built to accelerate development is now the vector for compromising it.

Hugging Face hosts 352,000 unsafe model issues. ClawHub's registry contains 341 malicious AI agent skills. The AI supply chain is now the most attractive target in software security.
Microsoft

When prompts become shells: RCE vulnerabilities in AI agent frameworks

New research exposes how prompt injection in AI agent frameworks can lead to remote code execution. Learn how these ...
The Hacker News

Weaver E-cology RCE Flaw CVE-2026-22679 Actively Exploited via Debug API

CVE-2026-22679 exploited via debug endpoint in Weaver E-cology before 20260312, enabling RCE and system compromise.

200,000 MCP servers expose a command execution flaw that Anthropic calls a feature

OX Security confirmed arbitrary command execution on six live platforms and estimates 200,000 MCP servers are exposed. Here's ...
Dark Reading

Google Fixes Critical RCE Flaw in AI-Based 'Antigravity' Tool

Google has fixed a critical flaw in its agentic integrated developer environment (IDE) Antigravity that led to sandbox escape and remote code execution (RCE) after researchers created a proof of ...
Hosted on MSN

OpenAI and Fortinet roll out major sandbox security upgrades

OpenAI has updated its Agents SDK with native sandbox execution and a refined harness to improve AI agent safety, while Fortinet patched critical FortiSandbox flaws enabling remote code execution and ...
InfoWorld

Claude Code is still vulnerable to an attack Anthropic has already fixed

Anthropic’s source code leak revealed a new way to get Claude Code to do things it doesn’t want to. The leak of Claude Code’s source is already having consequences for the tool’s security. Researchers ...
Polygon

Super Mario Bros. players uncover the biggest glitch in the game's 40-year history

Over 40 years after its release, you'd think that there would be no more secrets to be found in Super Mario Bros. A group of dedicated speedrunners just smashed that theory, discovering a ...