Show GN: AI한테 메일 맡기지 마라 — 인박스엔 비서가 아니라 '방화벽'이 필요하다 (오픈소스)
LLM-Scoring 기반의 결정론적 방화벽 구조를 통한 이메일 필터링 최적화
LLM-Scoring 기반의 결정론적 방화벽 구조를 통한 이메일 필터링 최적화
How to Stop LangChain Agents from Bankrupting Your API Budget
An AI "migrated" my site — and left it publicly exposed to the world (#71882)
Dynamic pricing on Shopify is not a pricing problem. It is a blast-radius problem.
Why AI Agents Need Runtime Budgets Before Provider Calls
Rate-Limit Your Own Agent Before Someone Else Does
Slack MCP Channel Allowlists: Stopping Agents Posting to #general
Workspaces: Policy Management for Fleets of Agents
Spam Detection for Inbound Agent Mail
Least Privilege for AI Agents: One Identity, One Scope
Restricting Attachments in Agent Inboxes
My safety guard protected 2 tools and trusted the other 20
Hardening API Scan Boundaries in skill-scanner, with sqry as the Review Map
llm-cli-gateway 2.5.0: OAuth for remote MCP connectors and safer workspaces
Stop Hardcoding 301s: How I Built a Redirect Engine That Doesn't Break at 2 A.M.
I built a circuit breaker for LLM agents after seeing someone lose $200 overnight
How I secured my FastAPI app - 6 vulnerabilities fixed in one session with gstack /cso
I got a $100 AI bill. Then I found the $80,000 ones. So I built a kill switch.(2026)
Why we built an Auth Gateway instead of putting auth in every service
nginx-ui's MCP endpoint shipped with 'empty allowlist equals allow-all' — and that's the story worth sitting with