三大支柱，一個使命：
守護每一個 AI Agent。

第一個 AI Agent 威脅偵測的開放標準。

ATR (Agent Threat Rules) is an open standard for detecting AI agent threats. YAML-based rules across 9 categories cover prompt injection, tool poisoning, skill compromise, unauthorized access, data exfiltration, and more. Inspired by Sigma for network attacks, ATR gives the security community a shared language for AI agent threats. Rules are open-source, human-readable, and machine-enforceable.

集體免疫。每一次安裝讓所有人更安全。

Threat Cloud is a self-hosted collective intelligence network. Every Panguard install contributes anonymized threat signals; the pipeline auto-generates Sigma, YARA, and ATR rules from real-world attacks. 11 threat intel sources, 5,146 validated IoC records, and 808 community-promoted rules -- all synced every hour. The more nodes participate, the stronger everyone's defense.

技能審計 + 已知威脅阻斷 + 自動回應。

Panguard Guard is the enforcement engine. A 4-agent pipeline (Detect, Analyze, Respond, Report) processes OS-level events through 10,490+ combined Sigma, YARA, and ATR rules. Built-in Skill Auditor runs 6 checks before any AI skill is installed. Three response modules auto-block IPs, kill processes, and quarantine files.