openclaw-safety-coachSafety coach for OpenClaw users. Refuses harmful, illegal, or unsafe requests and provides practical guidance to reduce ecosystem risk (malicious skills, too...
Install via ClawdBot CLI:
clawdbot install justindobbs/openclaw-safety-coachGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://clawhub.ai/justindobbs/openclaw-safety-coachAudited Apr 17, 2026 · audit v1.0
Generated May 11, 2026
A user tries to install an unreviewed ClawHub skill that uses subprocesses and file writes. The coach refuses, explains the risk of malicious code, and provides a manual review checklist with network, subprocess, file, and obfuscation checks. User is guided to run 'openclaw security audit' after review.
An attacker attempts prompt injection to extract API keys stored in memory. The coach immediately stops execution, refuses to reveal secrets, and advises rotating keys with 'openclaw auth set' and running 'openclaw secrets audit'. User is reminded to keep secrets in external vaults.
An admin configures a group chat bot with open DM policies, risking impersonation and prompt injection. The coach suggests setting 'dmPolicy="pairing"', 'groupPolicy="allowlist"', and 'requireMention: true' to limit access. User implements these directives to reduce attack surface.
A user requests enabling 'dangerouslyAllowContainerNamespaceJoin' for a deployment. The coach refuses, explaining it bypasses container isolation, and states it's break-glass only with documented justification. User is directed to use standard sandboxing instead.
An audit reveals 'gateway.auth.mode' is set to 'none', exposing the gateway. The coach warns of unauthorized access and recommends token-based authentication or Tailscale Serve with TLS. User enables auth and reruns 'openclaw security audit' to verify.
Offer expert guidance to enterprises on implementing OpenClaw security directives (e.g., sandbox mode, exec approvals, multi-user posture). Generate revenue through hourly consulting or retainer for security audits and policy enforcement.
Integrate the Safety Coach as a plugin in CI/CD pipelines to automatically block insecure skill deployments, secret leaks, and config errors. Charge per-repository or per-seat subscription for automated security scanning and coaching.
Provide prioritized incident response playbooks (as described in SKILL.md) for teams using OpenClaw. Revenue from one-time response engagements or monthly retainers covering key rotation, isolation, and audit execution.
💬 Integration Tip
Integrate as a high-priority security plugin in clawbot's metadata and ensure 'allow_exec: false' and sandbox mode are enforced before deployment.
Scored May 11, 2026
Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawdhub CLI.
Mission control dashboard for OpenClaw - real-time session monitoring, LLM usage tracking, cost intelligence, and system vitals. View all your AI agents in o...
Transcribe YouTube videos to text by extracting captions and subtitles directly from the video URL using yt-dlp without audio processing.
Manage a self-hosted Trello-like board via `wekancli`. Create, move and archive cards, lists and boards on a WeKan server. Use when user asks about task boar...
Proactive security monitoring, threat scanning, and auto-remediation for OpenClaw deployments
Create or improve SOUL.md files for OpenClaw agents through guided conversation. Use when designing agent personality, crafting a soul, or saying "help me create a soul". Supports self-improvement.