AWS fixed a Kiro prompt injection chain that rewrote mcp.json and launched attacker-controlled code with developer privileges ...

AWS Kiro prompt injection flaw let hidden web page text rewrite the IDE’s MCP configuration file and silently execute ...

Researchers uncover 7,600 FakeGit GitHub repos, including 800 AI skills and MCP lures spreading SmartLoader malware.

Webflow's updated Model Context Protocol server adds brand controls, permissions and analytics as marketing teams push AI agents into production websites.

Claude Code update v2.1.216 closes two permission bypass classes in auto mode — Bash compound-statement redirects and ...

Alex Salazar is the Co-Founder and CEO of Arcade.dev, a MCP runtime. Model context protocol (MCP) has been one of the most ...

A newly-disclosed exploit in Claude Code’s ‘auto-mode’ leaves developers facing remote code execution (RCE) vulnerabilities ...

Cursor IDE zero-day vulnerability: AI security firm Mindgard spent seven months trying to report a Windows code-execution ...

Straiker, The Agentic Security Company, today released the inaugural threat report from its STAR Labs team. To understand the real-world risk AI agents pose to enterprises, researchers ran thousands ...

Researchers reported the flaw to Cursor in December, but it still remains in the popular AI coding platform and can be used ...

New capability enables organizations to turn existing integrations, APIs, and business processes into governed MCP tools in minutesSan Mateo, California, July 01, 2026 (GLOBE NEWSWIRE) -- SAN MATEO, ...

A popular artificial intelligence (AI) coding tool can be exploited in just two clicks, allowing attackers to install permission-rich model context protocol (MCP) servers on privileged developers' ...