Browsing Tag
security
343 posts
Modelo pronto: carta de autorização para auditoria de segurança (escopo + regras de engajamento)
Toda auditoria começa por um documento que quase ninguém tem pronto: a autorização por escrito. Sem ela, você…
Google Locked Its AI Vulnerability Hunter Behind 650 Seats. Build Your Own for Under a Cent per File
On Tuesday, Google announced Gemini 3.8 Flash Cyber, a model that its own Cloud Vulnerability Research team used…
10,000 Agents, Zero Tokens: Why the Best AI Architectures “Skip” the LLM
1. Introduction: The Scalability Paradox of Agentic Systems In the boardroom, AI agents are promised as the ultimate…
Metrics Driven Security
Security teams have historically operated on instinct. A firewall rule feels right. A new tool seems like it…
macOS is LEGO. Linux is Minecraft. Notes from building the same app in both.
A Japanese version of this is on Note. Building an app for a Mac is like LEGO. The…
Auth for your MCP server, without running an authorization server
You built a remote MCP server. It’s useful, so now strangers’ agents want to call it, and you…
Hacking My Own Mac App: Penetration Testing macOS Defense Boundaries in a VM
A Japanese version of this is on Zenn. I build and sell a macOS network-security menu bar app…
Nobody searches for security apps. So I made mine a tool for AI agents instead.
A Japanese version of this is on Note. (This is Part 2 of the solo-security-dev series. Part 1…
AI wave
SOP – User Hardening Automation 1. Objective To automate Aerospike user hardening by removing unwanted users from the…
mcp-tool-sanitizer v0.1.0: Making the MCP approval-view match the bytes the model gets
mcp-tool-sanitizer v0.1.0: Making the MCP approval-view match the bytes the model gets A sanitizer that strips Unicode concealment…