# GH05TCREW/pentestagent

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

Repository: https://github.com/GH05TCREW/pentestagent
Canonical: https://ross.abutalabs.com/products/pentestagent
Language: Python
License: MIT
License Family: permissive
Topics: security-automation, ai-agents, ai, ai-cybersecurity, ai-hacking, ai-security-tool, ctf-tools, mcp-tools, pentesting-tools, red-teaming, ai-assistant, knowledge-graph, blackbox-testing, llm, penetration-testing
Last push: 2026-08-04T04:39:26+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 35, longevity 33
- inputs: {"age_days": 475, "days_push": 29, "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 3010, forks 605 (observed 2026-08-28T04:07:37.754579+00:00)

## What it is
PentestAgent is a Python-based AI agent framework for black-box penetration testing that orchestrates LLM-driven security testing workflows with a terminal UI and optional Docker-isolated tooling. It supports multiple LLM providers via LiteLLM, MCP tool integration, and ships pre-built Docker images including a Kali-based image with common pentesting tools.

## Use cases
- automate penetration testing with an AI agent
- run red team engagements assisted by LLMs
- solve CTF challenges with AI tooling
- manage bug bounty recon and testing workflows
- run pentesting tools in an isolated Docker container
- build custom AI security testing agents with MCP tools

## When to choose
- you want LLM-assisted black-box security testing with a TUI
- you need Docker-isolated execution of pentest tools
- you want to use any LiteLLM-supported model or a custom API relay
- you need MCP-compatible tooling for security automation

## When to avoid
- you need a compliant, audited commercial pentesting platform
- you want fully automated testing without human oversight or LLM API costs
- you need a lightweight scanner rather than an agent framework

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, penetration-testing, mcp, llm-inference, security, cli, terminal-ui
- domain: security, penetration-testing, large-language-models, developer-tools
- platform: python, windows, cli
- tags: pentesting, red-team, bug-bounty, blackbox-testing, ctf-tools, knowledge-graph, litellm, tui, ai-security, ai-agents, command-line, linux, macos, docker

## Member repositories
- GH05TCREW/pentestagent (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:37.754579+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 2026-08-30T07:30:12.173237+00:00, confidence not recorded.
  - readme: https://github.com/GH05TCREW/pentestagent (fetched 2026-08-28T04:07:37.754579+00:00, sha 283e01f303d5)
- Data as of 2026-08-30T08:39:29.467469+00:00.