Read access is not the threat model
Everyone is worried about AI reading things it shouldn't. That's the wrong threat model. The problem starts after the agent reads, and forty years of access control has nothing to say about it.
Tagged
ai-safety
3 posts
You locked down MCP. Skills walked in through the window
Skills bundle instructions, scripts, and MCP servers into a single installable package. That convenience is also the attack surface, and in February 2026 someone used it 335 times in three days.
Start here
What this blog is for, and what it is not.
