PwnClaw
AI Agent Security Testing — 112 attacks across 14 categories. Prompt injection, jailbreaks, MCP poisoning, agency hijacking & more. Test any AI agent in 5 minutes.
Cost / License
- Freemium (Subscription)
- Proprietary
Platforms
- Online
PwnClaw
Features
- Security Testing
- Agentic AI
- Model Context Protocol (MCP) Support
Tags
- ai-agent-security
- AI Agent
- agent-testing
- prompt-injection
- devsecops
- jailbreak
- ai-security
- red-teaming
- prompt-engineering
- cicd-security
- owasp
- ai-red-teaming
- llm-security
PwnClaw News & Activities
Recent activities
PwnClaw information
Developed by
ClawdeRaccoonLicensing
Proprietary and Freemium product.Pricing
Subscription ranging between $29 and $99 per month + free version with limited functionality.Written in
Alternatives
0 alternatives listedSupported Languages
- English
AlternativeTo Categories
AI Tools & Services, Security & Privacy, System & HardwareGitHub repository
- 1 Stars
- 0 Forks
- 0 Open Issues
- Updated
What is PwnClaw?
PwnClaw is an AI agent security testing platform that runs 112 real-world attacks against your AI agent to find vulnerabilities before attackers do.
It tests across 14 attack categories including prompt injection, jailbreaks, social engineering, data exfiltration, MCP poisoning, agency hijacking, and more. Each scan randomly selects up to 50 attacks and uses an AI judge to evaluate whether your agent was compromised.
After each scan, PwnClaw generates copy-paste fix instructions for every vulnerability found. In benchmarks, Gemini 3 Flash went from 87/100 to a perfect 100/100 score with just 5 fix instructions.
Features:
- No SDK or API keys required — just paste your agent's endpoint
- CI/CD API and GitHub Action for automated testing
- Benchmark percentiles comparing your agent against frontier models
- Markdown export for security documentation
- Free tier available (3 scans/month)
Repo on GitHub.