v1.4.2 released — 16 AI platform support, 101 ATR rules, OWASP Agentic Top 10 full coverage, 90,000+ skills scanned.
See changelog.
By the Numbers
| 101 detection rules | ATR (101) + community |
| 16 AI platforms | Claude Code, Claude Desktop, Cursor, OpenClaw, Codex, WorkBuddy, NemoClaw, ArkClaw, Windsurf, QClaw, Cline, VS Code Copilot, Zed, Gemini CLI, Continue, Roo Code |
| OWASP 10/10 | Full coverage of OWASP Agentic Top 10 for Agentic Applications 2026 |
| 3-layer AI pipeline | Rules engine, local AI (Ollama), cloud AI (Claude/OpenAI) |
| 11 MCP tools | Scan, audit, guard, threat search, and more |
| 8-check Skill Auditor | Gates every AI skill before install |
| 0 accounts required | No login, no signup, no API key needed to start |
OWASP Agentic Top 10: Full Coverage
ATR rules map to every category of the OWASP Top 10 for Agentic Applications 2026:| OWASP Category | ATR Rules | Coverage |
|---|---|---|
| ASI01: Agent Goal Hijack | 13 rules | STRONG |
| ASI02: Tool Misuse & Exploitation | 11 rules | STRONG |
| ASI03: Identity & Privilege Abuse | 9 rules | STRONG |
| ASI04: Agentic Supply Chain | 8 rules | STRONG |
| ASI05: Unexpected Code Execution | 8 rules | STRONG |
| ASI06: Memory & Context Poisoning | 8 rules | STRONG |
| ASI07: Inter-Agent Communication | 5 rules | MODERATE |
| ASI08: Cascading Failures | 4 rules | MODERATE |
| ASI09: Human-Agent Trust | 5 rules | MODERATE |
| ASI10: Rogue Agents | 7 rules | MODERATE |
Three Pillars
ATR -- The Standard
101 rules across 9 threat categories. The first open standard for AI agent threats — prompt
injection, tool poisoning, skill compromise, agent manipulation. YAML-based, human-readable,
machine-enforceable. OWASP Agentic Top 10: 10/10 covered.
Threat Cloud -- The Network
Collective immunity. Every install contributes anonymized threat signals. The pipeline
auto-generates rules from real-world attacks. 11 intel sources. Synced every hour.
Guard -- The Engine
4-agent AI pipeline. Detect, Analyze, Respond, Report. Processes OS-level events through 101
ATR rules. Built-in Skill Auditor. Auto-response blocks IPs, kills processes, quarantines files.
Quick Start
Install, scan, and protect in 4 commands:panguard setup auto-detects all 16 AI platforms on your machine and injects the correct MCP or native Skill configuration for each.
panguard guard start --dashboard starts 24/7 protection and opens a local dashboard in your browser at http://127.0.0.1:9100.
Step-by-step Quick Start
Detailed walkthrough with expected output for each step.
Installation Guide
Platform-specific instructions for macOS, Linux, and Windows.
Platform-Specific Setup
- Auto-detect all platforms
- OpenClaw
- NemoClaw
- ArkClaw
Who is Panguard AI for?
Developers
Secure your servers, VPS, and dev machines with zero configuration. One command, then back to
work.
Small Businesses
Compliance-ready security without a dedicated team. Auto-generate ISO 27001, SOC 2, and Taiwan
TCSA audit reports.
MSPs
Monitor and protect endpoints with real-time Guard protection.
Why Panguard AI?
Traditional security tools cost six figures and require dedicated teams. Free tools exist but are unusable without security engineers. Panguard takes a different approach:- One command install — no config files, no tuning, no jargon
- Plain language alerts — Telegram, Slack, Email, LINE in your preferred language
- AI auto-triage — the system judges severity, responds, and reports autonomously
- Gets smarter over time — behavioral baselines adapt to your environment
- Skill Auditor — gates every AI skill before install, prevents supply chain attacks
- 100% free — MIT licensed, no paid tiers, no feature gates, no paywalls
Research Paper
ATR is backed by a peer-reviewed research paper documenting the methodology, detection architecture, and evaluation results.Agent Threat Rules: A Community-Driven Detection Standard for AI Agent Security Published on Zenodo (DOI: 10.5281/zenodo.19178002). Under review at arXiv and SSRN.The paper covers: threat taxonomy, detection architecture (regex + LLM crystallization), PINT MCP benchmark evaluation (62.7% recall, 99.7% precision), SKILL.md benchmark (96.9% recall, 100% precision), and 64 documented evasion techniques.
100% Open Source
Every feature is free. Full source code. Zero black boxes. Every line is auditable.Panguard AI on GitHub
Star the repo, browse source, report issues, or contribute.
ATR Rules on GitHub
The open standard for AI agent threat detection. Contribute rules to strengthen collective
immunity.
Explore
Product Overview
Deep dive into the three pillars: ATR, Threat Cloud, and Guard.
CLI Reference
Complete command reference for every Panguard CLI tool.
API Reference
REST API docs for Threat Cloud.
Concepts
Understand the three-layer AI architecture powering Panguard.