Do Son New research explores AI generated code vulnerabilities within MCP server repositories. Learn why expert domain verification remains critical.
Model Context Protocol
A critical MCP Toolbox vulnerability exposes enterprise databases. Learn how this security flaw allows session hijacking and how to fix it.
Urgent: Casdoor IAM platform hit by critical file write flaw (CVE-2026-44213). Attackers can bypass sandboxes to overwrite databases and gain host access.
This week's digest: 1,214 new bugs, including active exploits on 2009 Excel fossils and critical 10.0 flaws in new AI/MCP infrastructure. Priority: Patch now.
Public PoC code and full details are out for a 9.8 CVSS flaw in Nginx UI (CVE-2026-33032). With no official patch, servers are at risk. Secure yours now!
Google’s experimental Workspace CLI ends the era of AI account bans, offering a "skills" bridge for agents like OpenClaw and Claude to automate Gmail and Drive.
Xcode 26.3 is out! Transform your workflow with Agentic Coding. Native Claude and Codex integration lets AI agents write, build, and test your apps for you.
OpenAI’s new App Directory lets ChatGPT summarize Dropbox files, order DoorDash, and manage Music directly, turning the AI into a true digital gateway.
Cymulate reveals two flaws (CVE-2025-53110, CVE-2025-53109) in Anthropic's Filesystem MCP Server, allowing path traversal, symlink attacks, and RCE, exposing AI developer machines.
A critical flaw (CVE-2025-5071) in WordPress's AI Engine plugin allows subscribers to escalate privileges and take over websites with Dev Tools/MCP enabled.
Windows 11 is set to become an "agentic" platform with the Model Context Protocol. Discover how Microsoft is bridging AI models with external data.
Google announces Gemini AI support for Anthropic's Model Context Protocol (MCP), aiming to standardize AI model integration with external tools and data, enhancing interoperability.