raptor

RAPTOR is an autonomous security research framework based on Claude Code, designed for vulnerability scanning, validation, and remediation.

Agent SkillDevOpen source

View source →

Type: Agent Skill
Open source: Yes
GitHub Stars: ★ 3.1k
Source: skill-github
Repository: github.com/gadievron/raptor

Overview

RAPTOR is an autonomous security research framework built upon Claude Code. It integrates static analysis, binary analysis, LLM-driven vulnerability validation, exploit generation, and patch creation into a unified workflow, capable of operating on codebases or binary files. By creating projects, rules, sub-agents, and skills, users can configure agents for adversarial thinking and perform research or offensive/defensive operations. Suitable for security researchers and developers.

Capabilities

▪Fully autonomous workflow: scanning, validation, exploitation, patching
▪Static analysis (Semgrep and CodeQL)
▪Attack surface mapping and data flow tracking
▪Multi-stage vulnerability exploitability validation
▪Binary fuzzing and crash analysis
▪Web application scanning

Use cases

Security audits of code repositoriesVulnerability detection in binary filesAutomated exploit generationSecurity patch generation

Setup

Requires: API KeyNode 环境Python 环境

git clone https://github.com/gadievron/raptor.git && cd raptor && pip install -r requirements.txt && npm install -g @anthropic-ai/claude-code && pip install semgrep && claude

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

What languages does RAPTOR support?

Supports multiple programming languages, depending on the tools used such as Semgrep and CodeQL.

How do I get started with RAPTOR?

Clone the repository and install dependencies, then run the `claude` command to begin.

Related skills

gemini-cli

Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.

MCP

private-gpt

Provides a complete API layer for local models, supporting RAG, skills, tools, and more.

MCP

planning-with-files

File-based persistent planning skill, ideal for AI coding agents and long-running tasks.

Agent Skill

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP