Security
PocketPaw implements defense-in-depth with multiple security layers. Every message is checked before processing, every action is logged, and tools are governed by a policy system.
Security Layers
Guardian AI
Secondary LLM evaluates every message for safety concerns. Messages classified as HIGH or CRITICAL are blocked.
Injection Scanner
Two-tier detection (regex + LLM) catches prompt injection in both user messages and tool outputs.
Tool Policy
Profiles and allow/deny lists control which tools are available.
Dangerous Command Blocking
PreToolUse hooks intercept and block dangerous shell commands.
Audit Log
Append-only JSONL log records every significant action.
Security Components
Guardian AI
Secondary LLM safety check on every incoming message.
Injection Scanner
Two-tier prompt injection detection for messages and tool outputs.
Audit Log
Append-only action recording in JSONL format.
Security Audit CLI
7 automated security checks with auto-fix option.
Self-Audit Daemon
12 continuous background checks with JSON reports.
PocketPaw is designed for self-hosted, single-user deployments. If exposing to multiple users, add authentication middleware to the web dashboard.