Skip to content
Agent Threat Rules (ATR)中文
Community

A standard is only as strong as the people who maintain it.

Sigma, CVE, and YARA became universal not because a company owned them, but because enough people chose to describe threats in one shared language. ATR follows the same path — contributors write rules, adopters wire them into production, researchers report the bypasses. Each one moves the standard a step closer to universal. A rule written in Taipei catches an attack first reported in Seattle.

What this community has shipped
836
detection rules
101,280
skills and MCP definitions scanned (engine v2.0.0, 2026-04-13)
10/10
OWASP Agentic categories, each with at least one rule that fires
30
ecosystem integrations
How to Contribute
Put your name on the wall.

Add one line to contributors.yaml and open a PR. Your GitHub avatar, country, and contribution types appear here — alongside everyone carrying an open standard toward universal. The list is public, and it stays.

Current Reach
🇹🇼
Taiwan
1 contributor
🇺🇸
United States
1 contributor

2 countries. A universal standard is worth as much as the number of places speaking the same language for threats. Goal: a contributor in every country running AI agents.