As AI systems begin interacting directly with enterprise tools through MCP, traditional gateway-based security models may not be enough…

As AI systems begin interacting directly with enterprise tools through MCP, traditional gateway-based security models may not be enough…

Burp AI Agent brings 53+ MCP tools and 62 vulnerability classes to Burp Suite. Automate scans, draft PoCs, and ensure privacy with local AI backends.

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.

The new agent communication protocols are repeating the unsigned-API era of the 2010s.

Urgent: Casdoor IAM platform hit by critical file write flaw (CVE-2026-44213). Attackers can bypass sandboxes to overwrite databases and gain host access.

Adversaries initiated a targeted reconnaissance campaign against vulnerable PraisonAI nodes less than four hours following the public disclosure of a critical security defect. An automated scanning entity identifying as CVE-Detector/1.0 launched offensives…

The Agentic SOC Era: Architecting Next-Generation Incident Response with Open Context Standardization

A critical MCP Toolbox vulnerability exposes enterprise databases. Learn how this security flaw allows session hijacking and how to fix it.

New research explores AI generated code vulnerabilities within MCP server repositories. Learn why expert domain verification remains critical.

I Audited 300 MCP-Related npm Packages. My Scanner Couldn’t Inspect Runtime Code in 217. So I created Driftward This is not a malware count. It is a warning about security reports that say “zero …

Introduction: The “One Token at a Time” Bottleneck

On September 11, 2026, a GitHub-reviewed advisory was published for the PyPI package mysql-mcp-server: its SSE transport validated neither…

Introduction

An MCP server is effectively an API that agents call for people, and that gives it an unusual set of risks. The caller is a model that text…