VulnClaw
Open-source AI penetration-testing agent that runs recon, exploitation and reporting from natural language.
Agent by Netw0rkNoob
IndexedMIT★ 3,794
Get started
Setup steps are in the repository. Website · Repository
About
VulnClaw is an open-source penetration-testing agent that runs from a CLI or a local web UI and takes natural-language requests. Its model-driven loop moves through information gathering, vulnerability discovery, exploitation and report generation, and it can produce Markdown reports and Python PoC scripts. It supports 13 LLM provider families, MCP tools for browser automation and HTTP traffic replay, and about 50 security skill references. The README limits use to authorized testing, CTF competitions, security teaching and red-team exercises.
Use cases: security, security-scanning
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Fact sheet
- Jobs
- securityREADME
- Autonomy
- Autonomous: runs tasks end to end and reports backREADME
- Where you use it
- Terminal, WebREADME
- Hosting
- You run itREADME
- Models
- openai, anthropic, minimax, deepseek, zhipu, moonshot, qwen, siliconflow, doubao, stepfun, sensetime, openrouter, ollamaREADME
- Interfaces
- mcp, agent-skillsREADME
- Open source
- YesREADME
Facts extracted by Claude Haiku 5.5 from the linked sources on Oct 24, 2026. Wrong fact? Tell us.
Signals
- Stars
- 3,794
- Forks
- 533
- Open issues
- 7
- Last commit
- Oct 5, 2026 (23 days ago)
- Last release
- Oct 6, 2026 (22 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Netw0rkNoob/VulnClaw
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- READMEgithub-graphql
Cite this page
VulnClaw. Agent Mart. https://agentmart.dev/agents/vulnclaw (last updated 2026-10-24)