An internal Google memo, first circulated in early April 2026 and since described by multiple people familiar with its ...

A multi-tenant authentication gap in Microsoft’s AI operations agent exposed live command streams, internal reasoning, and ...

Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's (MCP) architecture ...

A design flaw – or expected behavior based on a bad design choice, depending on who is telling the story – baked into ...

I don't really know why, though.

Unsafe defaults in MCP configurations open servers to possible remote code execution, according to security researchers who ...