# bugbasesecurity/pentest-copilot

Pentest Copilot is an AI-powered browser based ethical hacking assistant tool designed to streamline pentesting workflows.

Repository: https://github.com/bugbasesecurity/pentest-copilot
Canonical: https://ross.abutalabs.com/products/pentest-copilot
Homepage: https://pentest.bugbase.ai
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, cybersecurity, cybersecurity-tools, llms, pentesting
Last push: 2026-08-14T21:59:26+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 38
- inputs: {"age_days": 543, "days_push": 19, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1327, forks 251 (observed 2026-08-28T04:04:22.932266+00:00)

## What it is
Pentest Copilot is an open-source, AI-driven penetration testing agent that connects to a Kali attack box, autonomously runs security tools, analyzes results, and iterates on commands. It offers agentic execution with 16 built-in tools, Burp Suite integration, and a registry of 100+ security capabilities for real-world engagements, boot2root boxes, and CTFs.

## Use cases
- automate penetration testing workflows with an ai agent
- solve ctf and boot2root boxes autonomously
- integrate burp suite with an llm pentesting assistant
- run autonomous security tooling on a kali attack box
- find auth bypasses in web apps like owasp juice shop
- ai assistant for ethical hacking engagements

## When to choose
- you want an agentic AI to run pentest commands and iterate without manual nudging
- you need Burp Suite integration (proxy history, Repeater, Intruder, Collaborator) in an AI workflow
- you practice CTFs or boot2root machines and want automation
- you want a self-hosted, MIT-licensed alternative to closed pentest copilots

## When to avoid
- you need guaranteed-safe automation for production systems without human oversight
- you require a passive vulnerability scanner rather than an active agent
- you lack a Kali attack box or the infrastructure to run autonomous shell commands
- compliance policies prohibit LLM-driven execution on your targets

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, llm-inference, penetration-testing, security, developer-tools
- domain: penetration-testing, security, artificial-intelligence
- platform: self-hosted
- tags: pentesting, ethical-hacking, burp-suite, kali-linux, ctf, agentic-ai, offensive-security, ai-agents, web-server, linux, docker

## Member repositories
- bugbasesecurity/pentest-copilot (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:22.932266+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 2026-08-30T04:46:15.698563+00:00, confidence not recorded.
  - readme: https://github.com/bugbasesecurity/pentest-copilot (fetched 2026-08-28T04:04:22.932266+00:00, sha 6d8d24c50a52)
  - homepage: https://pentest.bugbase.ai (fetched 2026-08-29T12:05:21.050063+00:00, sha 2eecda42c706)
- Data as of 2026-08-30T08:39:29.467469+00:00.