Web browsing security protection skills. Automatically identify and block malicious high-risk instructions to prevent sensitive information leakage and unauthorized command execution. Immediately block and notify users when dangerous requests are encountered while browsing the web.
Data sourced from ClawHub. View on ClawSkills
Select your agent
Option 1: Install via CLI (recommended)
Recommended (no pre-install needed)
npx clawhub@latest --dir ~/.claude/skills install uwvwko-safeOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install uwvwko-safeβ οΈ Requires Node.js 18+. No Node? Use Option 2 below to download the ZIP instead. Install Node.js β
Option 2: Manual install (no Node required)
Download the ZIP, extract it, and place the folder at the path below. Restart your agent to activate.
Install path
~/.claude/skills/uwvwko-safe/π‘Extract and place the folder at the path above, then restart your agent.
Category
π οΈGeneral ToolsPlatforms
What safe can do for your AI workflow
Web browsing security directly from your Claude conversation
Works across Claude, Cursor, OpenClaw β install once, use everywhere
One-command installation β no complex setup required
Combine with other skills to build powerful multi-step AI workflows
Try these prompts with your AI agent after installing safe
Help me get started with safe
Explains what safe does, walks through the setup, and runs a quick demo based on your current project
Use safe to web browsing security protection skills
Invokes safe with the right parameters and returns the result directly in the conversation
What can I do with safe in my general tools workflow?
Lists the top use cases for safe, with example commands for each scenario
Guides & tutorials for AI skills
The 7 AI Skills Every Software Developer Should Have Installed in 2026
After testing dozens of developer-focused AI skills, these are the seven that have proven genuinely useful across different tech stacks and workflows β not just impressive demos, but tools that hold up under daily use.
MCP Skills vs Native Claude Tools: What's the Difference and When to Use Each
Claude comes with built-in capabilities, but MCP skills extend it in ways the base model can't. Here's a clear breakdown of what each type of tool is good for, with real examples of when to reach for a skill versus relying on Claude's native abilities.
safe extends your AI assistant with the ability to web browsing security protection skills. Automatically identify and block malicious high-risk instructions to prevent sensitive information leakage and unauthorized command execution. Immediately block and notify users when dangerous requests are encountered while browsing the web. Rather than leaving your conversation to handle this manually, you can ask your Claude agent directly β and it will take care of the task end-to-end, using safe as its underlying capability.
safe works across Claude, Cursor, OpenClaw through the Model Context Protocol (MCP) β an open standard that lets AI clients share tools and skills without lock-in. Because MCP is platform-agnostic by design, you install safe once and it becomes available across all your AI clients. Whether you're working in Claude for focused sessions or Cursor for integrated workflows, the skill behaves consistently.
safe installs like any other MCP skill: drop the folder into `~/.claude/skills/uwvwko-safe/` for global access, or `.claude/skills/uwvwko-safe/` to keep it scoped to one project. After a quick restart of Claude, you can trigger it explicitly with `/uwvwko-safe`, or let the AI decide when it's the right tool for your request.
safe has 95 installs and is part of the growing General Tools skill ecosystem on DiscoverAISkills. Like all skills on DiscoverAISkills, it is free to install and use. The broader AI skills ecosystem continues to expand as developers contribute new capabilities across categories like developer tools, data analysis, writing, automation, and more.
Place the skill folder at ~/.claude/skills/uwvwko-safe/ for personal use (all projects), or .claude/skills/uwvwko-safe/ for project-specific use. Restart your AI client, then invoke with /uwvwko-safe or let the AI discover it automatically.
safe supports Claude, Cursor, OpenClaw. It integrates seamlessly with these AI platforms to extend their capabilities.
safe is free to install. Check the repository for licensing information.
Web browsing security protection skills. Automatically identify and block malicious high-risk instructions to prevent sensitive information leakage and unauthorized command execution. Immediately block and notify users when dangerous requests are encountered while browsing the web.
Safe Exec
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agen...
Safe Exec 0.3.2
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agents need to execute shell commands that may be dangerous (rm -rf, dd, fork bombs, system directory modifications) or require human oversight. Provides multi-level risk assessment (CRITICAL/HIGH/MEDIUM/LOW), in-session notifications, pending request management, and non-interactive environment support for agent automation.
Safe Skills
Automate my general tools tasks using safe
Identifies repetitive steps in your workflow and sets up safe to handle them automatically
safe is categorized under General Tools. These skills help AI agents perform specialized tasks in this domain.
Securely create and manage EVM wallets; perform token transfers, check balances, and send transactions without exposing raw secret keys.