#63 · Primary category: Cybersecurity & Decryption Tools

pentestagent

ai ai-agents ai-assistant ai-cybersecurity ai-hacking ai-security-tool blackbox-testing ctf-tools knowledge-graph llm mcp-tools penetration-testing pentesting-tools red-teaming security-automation

PentestAgent is an AI agent framework for black-box security testing, supporting bug bounty, red-team, and penetration testing workflows.

Project last updated:08/28/26

GitHub Stars

3.0K

Forks

608

Contributors

13

License

MIT

Why we included this project

PentestAgent is for security testers who want to speed up black-box assessments without losing control of the process. It's a Python agent built on LiteLLM, so you can drive it with Anthropic, OpenAI, or any other provider you already have access to, and it runs the actual tools (nmap, sqlmap, msfconsole, a browser) either locally or inside an isolated Docker container. Beyond one-shot assistance, it offers autonomous single-task agents, an orchestrator that spawns isolated child agents to parallelize recon, guided interactive chat, and prebuilt playbooks with structured attack workflows for web targets. MCP compatibility means you can wire in your own server tools, and running everything in a Kali-based container keeps your host machine clean while the agent does its work.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category