JuliusHenke/autopentest
CLI enabling more autonomous black-box penetration tests using Large Language Models (LLMs)
This tool helps cybersecurity professionals and researchers automate black-box penetration tests, which assess system vulnerabilities without prior knowledge of internal workings. It takes a target IP address or domain as input and autonomously performs multi-step security assessments using AI, identifying potential weak points. The primary users are security analysts, vulnerability management teams, and cybersecurity researchers looking to streamline their testing workflows.
Use this if you need to perform autonomous black-box penetration tests on systems you have explicit permission to test, using AI agents to find vulnerabilities.
Not ideal if you require a production-ready, fully certified vulnerability scanning solution, or if you intend to use it for unauthorized or illegal activities.
Stars
43
Forks
6
Language
Python
License
—
Category
Last pushed
Mar 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/JuliusHenke/autopentest"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LLAMATOR-Core/llamator
Red Teaming python-framework for testing chatbots and GenAI systems.
sleeepeer/PoisonedRAG
[USENIX Security 2025] PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented...
kelkalot/simpleaudit
Allows to red-team your AI systems through adversarial probing. It is simple, effective, and...
SecurityClaw/SecurityClaw
A modular, skill-based autonomous Security Operations Center (SOC) agent that monitors...
AI-secure/AgentPoison
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or...