# BishopFox/eyeballer

Convolutional neural network for analyzing pentest screenshots

Repository: https://github.com/BishopFox/eyeballer
Canonical: https://ross.abutalabs.com/products/eyeballer
Language: Python
License: GPL-3.0
License Family: copyleft
Topics: security-tools, machine-learning, ai, python, tensorflow, pentesting-tools
Last push: 2026-03-08T20:43:54+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 71, release rhythm 8, longevity 100
- inputs: {"age_days": 2737, "days_push": 178, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1290, forks 148 (observed 2026-08-28T04:04:15.476618+00:00)

## What it is
Eyeballer is a convolutional neural network tool that classifies screenshots of web hosts taken during large-scope penetration tests. It labels images as old-looking sites, login pages, webapps, custom 404s, or parked domains to help pentesters prioritize interesting targets.

## Use cases
- classify pentest screenshots of web hosts
- find vulnerable-looking old websites at scale
- identify login pages for credential attacks
- filter out custom 404 pages and parked domains
- triage EyeWitness or GoWitness screenshot output

## When to choose
- you have thousands of web screenshots from a large-scope pentest and need to prioritize targets
- you want ML-based classification instead of brittle heuristics for login page detection

## When to avoid
- you need real-time or API-based analysis rather than batch screenshot classification
- your scope is small enough to review screenshots manually

## Facets
- artifact type: cli-tool
- maturity: active
- function: machine-learning, image-processing, computer-vision, security
- domain: security, machine-learning, penetration-testing
- platform: python, cli
- tags: pentesting, screenshot-analysis, cnn, tensorflow, bishopfox, linux, macos

## Member repositories
- BishopFox/eyeballer (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:15.476618+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 2026-08-30T04:54:50.247800+00:00, confidence not recorded.
  - readme: https://github.com/BishopFox/eyeballer (fetched 2026-08-28T04:04:15.476618+00:00, sha 7ec8095d5a97)
- Data as of 2026-08-30T08:39:29.467469+00:00.