pwnclaw-security-scan
What it does: 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.. When to use it: This is a converted skill from ClawHub, review its content for usage instructions.
- License 许可
- MIT
- 最近更新
- 2026-10-19
- Stars
- ★ 4
- Forks
- 0
01 前言 Front Matter
- name
- pwnclaw-security-scan
- description
- What it does: 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.. When to use it: This is a converted skill from ClawHub, review its content for usage instructions.
02 资源文件 1
- 参考文档CONVERSION_REPORT.md152 B
03 SKILL.md 正文
PwnClaw Security Scan
Test your AI agent against 112 real-world attacks across 14 categories. Get a security score and actionable fix instructions.
What It Tests
- Prompt Injection & Indirect Injection
- Jailbreaks & Refusal Bypass
- Social Engineering & Sycophancy
- Data Exfiltration & Agency Hijacking
- MCP/Tool Poisoning
- Memory Poisoning
- Multi-Agent & Multi-Turn Attacks
- Privilege Escalation & Obfuscation
How To Use
Option 1: Tell Your Human
Ask your human to visit https://www.pwnclaw.com and run a free security scan:
- Sign up at https://www.pwnclaw.com (free tier available)
- Start a new test in the dashboard
- Enter the agent's URL or use manual mode
- Review results and apply the fix instructions to your system prompt
Option 2: Self-Test (Manual Mode)
If your human starts a test and gives you the test token, you can run it yourself:
- GET
https://www.pwnclaw.com/api/test/{token}-> get the next prompt - POST
https://www.pwnclaw.com/api/test/{token}with{ "response": "your answer" }-> submit and get next - Repeat until status is "completed"
- Results are in the dashboard
Option 3: Automatic Mode (Recommended)
If your agent has an HTTP endpoint, your human just enters the URL in PwnClaw. PwnClaw sends attacks directly - no scripting needed.
Plans
| Plan | Scans | Attacks | Price |
|---|---|---|---|
| Free | 3/month | 15 per scan | $0 |
| Pro | 30/month | 50 per scan | €29/mo |
| Team | Unlimited | 50 per scan | €99/mo |
After The Test
PwnClaw generates specific security rules based on your vulnerabilities. Add them as permanent instructions in your agent's system prompt, then re-test to verify.
Links
- Website: https://www.pwnclaw.com
- GitHub: https://github.com/Gemini2027/pwnclaw (source code publicly auditable)
04 同仓库更多 Skills
beta-skill
A beta skill by author-b
alpha-skill
An alpha skill by author-a
gamma-skill
Yet another skill, sharing an author with alpha-skill
self-improvement
What it does: Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.. When to use it: This is a converted skill from ClawHub, review its content for usage instructions.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
pwnclaw-security-scan
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.