Test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your agent needs a security check or hardening.
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 pwnclaw-security-scanOr via clawhub CLI (if already installed)
clawhub --dir ~/.claude/skills install pwnclaw-security-scanβ 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/pwnclaw-security-scan/π‘Extract and place the folder at the path above, then restart your agent.
Category
π»Developer & DevOpsPlatforms
What PwnClaw Security Scan can do for your AI workflow
Your ai agent for security directly from your Claude conversation
Works across Claude, Cursor, OpenClaw β install once, use everywhere
Trusted by 1,183+ developers worldwide
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 PwnClaw Security Scan
Help me get started with PwnClaw Security Scan
Explains what PwnClaw Security Scan does, walks through the setup, and runs a quick demo based on your current project
Use PwnClaw Security Scan to test your AI agent for security vulnerabilities using PwnClaw
Invokes PwnClaw Security Scan with the right parameters and returns the result directly in the conversation
What can I do with PwnClaw Security Scan in my developer & devops workflow?
Lists the top use cases for PwnClaw Security Scan, with example commands for each scenario
Guides & tutorials for AI skills
10 Fresh GitHub Agent Skills Added in June 2026
A hand-checked shortlist of recently updated GitHub agent skills that were not already in our catalog, excluding marketplaces, awesome lists, managers, and generic skill directories.
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.
PwnClaw Security Scan extends your AI assistant with the ability to test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your agent needs a security check or hardening. 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 PwnClaw Security Scan as its underlying capability.
PwnClaw Security Scan 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 PwnClaw Security Scan 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.
To install PwnClaw Security Scan, copy the skill folder to `~/.claude/skills/pwnclaw-security-scan/` for use across all your projects, or `.claude/skills/pwnclaw-security-scan/` for a single project. Restart Claude and the skill is immediately active β invoke it with `/pwnclaw-security-scan` or just describe your goal and the AI will pick it up automatically.
PwnClaw Security Scan has been installed 1,183 times, making it one of the more actively used skills in the Developer & DevOps category. The install rate suggests it solves a real, recurring need rather than a niche edge case. 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/pwnclaw-security-scan/ for personal use (all projects), or .claude/skills/pwnclaw-security-scan/ for project-specific use. Restart your AI client, then invoke with /pwnclaw-security-scan or let the AI discover it automatically.
PwnClaw Security Scan supports Claude, Cursor, OpenClaw. It integrates seamlessly with these AI platforms to extend their capabilities.
PwnClaw Security Scan is free to install. Check the repository for licensing information.
Test your AI agent for security vulnerabilities using PwnClaw. Runs 50+ attacks (prompt injection, jailbreaks, social engineering, MCP poisoning, and more) and provides fix instructions. Use when your agent needs a security check or hardening.
Security Auditor
CuratedUse when reviewing code for security vulnerabilities, implementing authentication flows, auditing OWASP Top 10, configuring CORS/CSP headers, handling secrets, input validation, SQL injection prevention, XSS protection, or any security-related code review.
Security Audit Toolkit
CuratedAutomate my developer & devops tasks using PwnClaw Security Scan
Identifies repetitive steps in your workflow and sets up PwnClaw Security Scan to handle them automatically
PwnClaw Security Scan is categorized under Developer & DevOps. These skills help AI agents perform specialized tasks in this domain.
Audit codebases and infrastructure for security issues. Use when scanning dependencies for vulnerabilities, detecting hardcoded secrets, checking OWASP top 10 issues, verifying SSL/TLS, auditing file permissions, or reviewing code for injection and auth flaws.