Security compliance

Verify agent-to-agent communication against session type protocols. Mathematical proofs, not trust.

MTProto 2.0 protocol implementation guide for Telegram backend development. Use when implementing MTProto encryption, handshake, message ser...

Use when auditing and remediating an OpenClaw Linux host with a nightly 23:00 security run. Covers firewall status, fail2ban bans, SSH harde...

Backup and restore OpenClaw data. Use when user asks to create backups, set up automatic backup schedules, restore from backup, or manage ba...

Backup and restore OpenClaw data. Use when user asks to create backups, set up automatic backup schedules, restore from backup, or manage ba...

This skill should be used when the user asks for daily backup, scheduled backup, restore, rollback, recovery, or routine protection of core ...

OpenClaw Gateway Guardian - Automatic monitoring, protection, and restart of OpenClaw Gateway service. Prevents gateway from stopping, crash...

This skill should be used when the user asks to test OpenClaw recovery readiness, rehearse backup/restore, run a disaster-recovery drill, va...

Enterprise AI security scanner combining static code analysis, runtime guards, ClamAV integration, and tamper-proof audit logging to detect ...

This skill should be used when the user asks to reduce OpenClaw token spend, audit model and cron cost risk, prevent denial-of-wallet incide...

This skill should be used when the user asks for an OpenClaw health check, OpenClaw security audit, server hardening review, exposure review...

Escrow + trust scoring on Base mainnet. Checks 24K+ agents BEFORE you pay. Real dispute resolution. Works with any x402 API — vendor doesn'...

Secure multi-chain wallet for AI agents. Create wallets, check balances, sign and broadcast transactions across 12 chains (EVM + Solana + TO...

A partnership covenant for AI agents and their human operators. v1.1 adds the Subagent Responsibility Chain and Inspectability Clause.

Protects sensitive files (contracts, transaction data, personal/customer privacy) by performing deep content inspection for text and binary ...

跨平台代理管理助手 (Universal Proxy Manager)。自动检测环境，首次使用自动安装，后续自动管理。支持 Windows/Linux/macOS，一键开启/关闭/切换节点/更新...

Medical device risk management specialist implementing ISO 14971 throughout product lifecycle. Provides risk analysis, risk evaluation, risk...

Safety Guard URLs or files with the safety-guard CLI (web, PDFs, images, audio, YouTube).

Security guard skill for OpenClaw - Analyzes user input for harmful content, risky commands, and security threats before invoking LLM

Security guard skill for OpenClaw - Analyzes user input for harmful content, risky commands, and security threats before invoking LLM

Scan ClawHub skills for security vulnerabilities BEFORE installing. Use when installing new skills from ClawHub to detect prompt injections,...

安全技能安装管理器 - 按照用户要求，所有技能安装前必须通过Skill vetter检测，如果发现需要修改配置的直接拒绝并上报，所有指令以用户为准。...

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, p...

Evaluate any AI agent's soul file, system prompt, or AGENTS.md against the Guardian v0.7 framework (Forrest Landry's Immanent Metaphysics). ...

【最高优先级】操作守卫。任何工具调用前必须先完成权限检查！AI 在执行任何非日常对话的操作前，必须先调用 permission-gate 验证权限。...