CyberStrike
An AI-powered offensive security agent supporting over 7,300 security techniques.
- Type
- Agent Skill
- Open source
- Yes
- GitHub Stars
- ★ 1.0k
- Source
- skill-github
- Repository
- github.com/CyberStrikeus/CyberStrike
Overview
CyberStrike is an AI-driven offensive security agent offering over 7,300 actionable security techniques. It performs autonomous penetration testing using MITRE ATT&CK (over 2,000 atomic tests), CIS Controls (over 1,500 controls), OWASP, and NIST frameworks. Supports lazy loading and zero context pollution. Connect your LLM provider (e.g., Claude or GPT) to transform it into an autonomous red team agent. Ideal for security teams needing automated penetration testing.
Capabilities
- ▪Over 7,300 security techniques
- ▪Autonomous penetration testing based on MITRE ATT&CK
- ▪Supports CIS benchmarks, OWASP, and NIST
- ▪Lazy loading and zero context pollution
- ▪13 specialized agents and over 120 OWASP test cases
Use cases
Setup
npm i -g @cyberstrike-io/cyberstrike@latest && cyberstrike
This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.
FAQ
How do I get started with CyberStrike?
After installation, run `cyberstrike`, then enter your LLM provider and API key to begin.
Which LLM providers are supported?
Supports over 15 providers including Anthropic, OpenAI, Google, and more.
Related skills
gemini-cli
Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.
private-gpt
Provides a complete API layer for local models, supporting RAG, skills, tools, and more.
planning-with-files
File-based persistent planning skill, ideal for AI coding agents and long-running tasks.
scientific-agent-skills
Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.
susi_alexa_skill
A skill that enables question-and-answer interactions between Alexa and Susi AI.
claude-context
Provides code search capabilities for Claude Code, turning the entire codebase into context.