Harden an OpenClaw Linux server with SSH key-only auth, UFW firewall, fail2ban brute-force protection, and credential permissions. Use when setting up a new...
AI security scanner with active prevention - 168 detection patterns, 288 attack probes, safer/risky/yolo modes, agent self-protection via /tinman check, loca...
AI-powered cryptocurrency safety assistant with database-first architecture. Protects users from phishing, honeypots, rug pulls, and ponzi schemes. No extern...
Self-healing backup and update system with intelligent rollback. Protects against failed updates by automatically monitoring system health post-update and recovering from backups when needed. Features
Anti-detect browser automation using Camoufox (Firefox-based). Use instead of Chrome/Playwright for bot-detection-heavy sites like X/Twitter, Naver, and other protected sites. Provides stealth browsin
Security layer protecting agents from prompt injection, social engineering, and malicious content on Moltbook and similar platforms. Scan content before processing, detect threats, block attacks.
Integrate PromptDome prompt injection screening into OpenClaw. Use when setting up automatic protection against prompt injection, jailbreaks, and PII exfiltr...
MoltGuard — Protect you and your human from prompt injection, data exfiltration, and malicious commands. Source: https://github.com/openguardrails/openguardr...
Local PII protection for OpenClaw agents. Scrubs customer data (names, phones, emails, addresses, credit cards, vessel names) before it reaches any AI model....
Three-layer protection for the OpenClaw gateway: real-time config monitoring with auto-rollback, systemd crash recovery, and tiered notifications via Feishu/...
Five-layer security for AI agents — prompt injection defense, secret protection, PII scanning
Enforces MFA by requiring a secret word to access protected sensitive data and allows emergency reset with a super secret word.
Streamline approval for non-standard deals by enforcing discount limits, validating deal value, and managing custom terms to protect margin and speed closing.
--- name: korean-scraper description: Korean website specialized scraper with anti-bot protection (Naver, Coupang, Daum, Instagram) version: 1.0.0 author: 무펭이 🐧 --- # korean-scraper **한
AI Agent Skill Security Scanner - Detect malicious skills, verify signatures, analyze permissions, and provide trust ratings for the agent ecosystem. Protect...
Navigate legal strategy with contracts, compliance, IP protection, and corporate governance.
CornerStone MCP x402 skill for agents. Tools for stock predictions, backtests, bank linking, and agent/borrower scores. Payment-protected MCP tools (run_prediction, run_backtest, link_bank_account, ge
GoPlus AgentGuard — AI agent security guard. Automatically blocks dangerous commands, prevents data leaks, and protects secrets. Use when reviewing third-par...
Run Scrapclaw as a Dockerized browser-backed scraping service, then use this skill to fetch HTML from JavaScript-heavy or Cloudflare-protected pages through...
Security monitoring and threat detection for OpenClaw agents — protect your agent with real-time SIEM, detect threats, monitor agent activity, and audit even...
Advanced prompt injection defense with multi-layer protection, memory integrity, and tool security wrapper. OWASP LLM Top 10 2026 compliant.
Authentication and authorization patterns — JWT, OAuth 2.0, sessions, RBAC/ABAC, password security, MFA, and vulnerability prevention. Use when implementing login flows, protecting routes, managing
Stealth-first browser automation for OpenClaw using agent-browser-stealth. Use when tasks involve bot-protected websites, anti-fingerprint evasion, captcha-p...
Safety monitoring and tripwire detection for AI agents. Protects against unauthorized file access, dangerous commands, and excessive activity. Auto-halts on...