# ipa-lab/hackingBuddyGPT

Helping Ethical Hackers use LLMs in 50 Lines of Code or less..

Repository: https://github.com/ipa-lab/hackingBuddyGPT
Canonical: https://ross.abutalabs.com/products/hackingbuddygpt
Homepage: https://hackingbuddy.ai/
Language: Python
License: MIT
License Family: permissive
Topics: large-language-models, llm, penetration-testing, pentesting
Last push: 2026-08-21T17:54:36+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 21, longevity 80
- inputs: {"age_days": 1127, "days_push": 12, "days_rel": 371, "gap_med": 124, "n_releases_24m": 2}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1223, forks 209 (observed 2026-08-28T04:04:02.590329+00:00)

## What it is
HackingBuddyGPT is a Python framework that helps ethical hackers and security researchers use LLMs and LLM-based autonomous agents for penetration testing, aiming for minimal-code experimentation. It includes reusable Linux privilege-escalation benchmarks and supports SSH and local shell execution against targets.

## Use cases
- automate penetration testing with llm agents
- find linux privilege escalation vulnerabilities with ai
- use llms to discover attack vectors
- build an ai hacking agent for security testing
- benchmark llms on security tasks
- earn bug bounties using ai-assisted hacking

## When to choose
- you are a security researcher or pentester experimenting with LLM-driven agents
- you want a lightweight, hackable framework for AI-assisted security testing
- you need priv-esc benchmarks to evaluate LLMs on security tasks

## When to avoid
- you need a production-grade, fully automated pentesting product
- you cannot run commands in an isolated environment, since it executes commands on live targets
- you are not comfortable with experimental research software

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, penetration-testing, security
- domain: security, penetration-testing, artificial-intelligence, large-language-models
- platform: python, cli
- tags: ethical-hacking, pentesting, llm-agents, privilege-escalation, security-research, bug-bounty, ai-agents, linux

## Member repositories
- ipa-lab/hackingBuddyGPT (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:02.590329+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:15:33.160627+00:00, confidence not recorded.
  - readme: https://github.com/ipa-lab/hackingBuddyGPT (fetched 2026-08-28T04:04:02.590329+00:00, sha ca9f4f90dd05)
  - homepage: https://hackingbuddy.ai/ (fetched 2026-08-29T12:24:09.968528+00:00, sha ac69aa933937)
  - registry_pypi: https://pypi.org/pypi/hackingbuddygpt/json (fetched 2026-08-29T12:24:09.977452+00:00, sha e3f5b85998cf)
- Data as of 2026-08-30T08:39:29.467469+00:00.