ibndias/CIPHER

Cybersecurity Intelligent Pentesting Helper for Ethical Researcher (CIPHER). Fine tuned LLM for penetration testing guidance based on writeups.

32
/ 100
Emerging

This project helps cybersecurity professionals and ethical hackers evaluate the guidance provided by large language models during penetration testing. It takes existing penetration test writeups and processes them into a structured format called FARR Flow (Findings, Action, Reasoning, Result). The output is a performance score for how accurately an LLM guides users through a simulated penetration test, helping you understand an AI's effectiveness in this complex domain.

No commits in the last 6 months.

Use this if you need to objectively measure how well an AI model can guide a penetration tester through identifying vulnerabilities and executing exploits, based on real-world expert knowledge.

Not ideal if you are looking for a standalone penetration testing tool or a simple chatbot to answer general cybersecurity questions.

penetration-testing ethical-hacking cybersecurity-training vulnerability-assessment LLM-evaluation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 17 / 25

How are scores calculated?

Stars

37

Forks

8

Language

Python

License

Last pushed

Dec 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ibndias/CIPHER"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.