VulnClaw

VulnClaw

A penetration testing tool based on AI Agent and MCP toolchain, supporting natural language input.

Agent SkillDevOpen source
Type
Agent Skill
Open source
Yes
GitHub Stars
★ 2.7k
Source
skill-github

Overview

VulnClaw is a CLI-based penetration testing tool built on AI Agent and the MCP toolchain. It automates the entire workflow—information gathering, vulnerability discovery, exploitation, and report generation—from natural language input. Suitable for authorized penetration testing, CTF competitions, security education, and red team exercises. Users can configure different LLM providers to use the tool and support various encoding and decoding operations. VulnClaw also offers a Web UI mode for interactive use.

Capabilities

  • Information Gathering: Fingerprinting, port scanning, directory enumeration
  • Vulnerability Discovery: Detecting injection points, known CVEs, configuration flaws
  • Exploitation: PoC validation, privilege escalation
  • Report Generation: Structured reports + Python PoC scripts
  • 14 LLM Provider Support
  • 29 Encoding/Decoding and Encryption/Decryption Operations

Use cases

Authorized Penetration TestingCTF CompetitionsSecurity EducationRed Team Exercises

Setup

Requires: API KeyPython 3.10+
pip install vulnclaw or install from source: git clone https://github.com/Netw0rkNoob/VulnClaw.git; cd VulnClaw; pip install -e .

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

FAQ

How to select an LLM provider?

Use the command `vulnclaw config provider <provider>`.

How to set the API Key?

Use the command `vulnclaw config set llm.api_key <your-key>`.

Related skills