slowmist/openclaw-security-practice-guide

A complete security skill suite for OpenClaw, Hermes, PicoClaw and NanoClaw agents (and variants). Protect your SOUL.md (etc') with drift detection, live security recommendations, automated audits, and skill integrity verification. All from one installable suite.

Unofficial OpenClaw runbook for running agents day to day without burning money, exposing your gateway, or trusting random automation.

Security Governance for Agentic AI

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

OpenShell is the safe, private runtime for autonomous AI agents.

Security firewall for agents

Deterministic security for real-world agentic applications

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drift in real time, before the agent acts.

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka The Norton for OpenClaw)