BreachWatch
cognis-digital/breachwatch
Agregador de violações pessoais com HIBP, DeHashed e triagem de stealer-logs
Ver no GitHubAgregador pessoal de violações de dados que integra HIBP, DeHashed e análise de logs de roubo. Oferece triagem inteligente de vulnerabilidades sem infraestrutura pesada, auto-hospedável e nativo para MCP, ideal para CI/CD e agentes de IA.
Instalação
npx convez-ai cognis-digital/breachwatch1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Monitorar exposição pessoal de dados em múltiplas bases de violações
- Integrar análise de breaches em pipelines CI/CD
- Dar controle indivíduos sobre seus dados e histórico de exposição
- Automatizar triagem de severidade de vulnerabilidades com agentes IA
Veredito

BreachWatch é solução elegante e focada para quem precisa monitorar exposição pessoal sem overhead operacional. Suporte nativo a MCP e saída estruturada (JSON/SARIF) o tornam valioso para automação e CI/CD.
README
A tradução para o português deste README ainda está na fila.
BREACHWATCH
Personal breach aggregator — HIBP + DeHashed + stealer-log triage
Privacy / Personal — put individuals back in control of their data.
pip install cognis-breachwatch
breachwatch scan . # → prioritized findings in seconds
Contents
- Why breachwatch? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing
Why breachwatch?
Personal breach aggregator — HIBP + DeHashed + stealer-log triage — without standing up heavyweight infrastructure.
breachwatch is single-purpose, scriptable, and self-hostable: point it at a target, get prioritized results in the format your workflow already speaks (table · JSON · SARIF), gate CI on it, and let agents drive it over MCP.
Features
- ✅ Redact
- ✅ Severity For
- ✅ Parse Hibp
- ✅ Parse Dehashed
- ✅ Parse Stealer Log
- ✅ Triage
- ✅ Load Sources
- ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
- ✅ Ports in Python, JavaScript, Go, and Rust (
ports/)
Quick start
pip install cognis-breachwatch
breachwatch --version
breachwatch scan . # scan current project
breachwatch scan . --format json # machine-readable
breachwatch scan . --fail-on high # CI gate (non-zero exit)
Example
$ breachwatch scan .
[HIGH ] BRE-001 example finding (./src/app.py)
[MEDIUM ] BRE-002 another signal (./config.yaml)
2 findings · risk score 5 · 38ms
Architecture
flowchart LR
A[Input: file / dir / API] --> B[Collectors]
B --> C[Rules / Analyzers]
C --> D[Scorer]
D --> E{Reporters}
E --> F[Table]
E --> G[JSON / SARIF]
E --> H[MCP tool -. drives .-> AI agents]
Use it from any AI stack
breachwatch is interoperable with every popular way of using AI:
- MCP server —
breachwatch mcp(Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet) - OpenAI-compatible / JSON — pipe
breachwatch scan . --format jsoninto any agent or LLM - LangChain · CrewAI · AutoGen · LlamaIndex — wrap the CLI/JSON as a tool in one line
- CI / scripts — exit codes + SARIF for non-AI pipelines
How it compares
| Cognis breachwatch | typical tools | |
|---|---|---|
| Self-hostable, no account | ✅ | varies |
| Single command, zero config | ✅ | ⚠️ |
| JSON + SARIF for CI | ✅ | varies |
| MCP-native (AI agents) | ✅ | ❌ |
| Polyglot ports (JS/Go/Rust) | ✅ | ❌ |
| Open license | ✅ COCL | varies |
Integrations
Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (breachwatch mcp) for AI agents, and a webhook forwarder for SIEM/Slack/Jira. See docs/INTEGRATIONS.md.
Install — every way, every platform
pip install "git+https://github.com/cognis-digital/breachwatch.git" # pip (works today)
pipx install "git+https://github.com/cognis-digital/breachwatch.git" # isolated CLI
uv tool install "git+https://github.com/cognis-digital/breachwatch.git" # uv
pip install cognis-breachwatch # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/breachwatch:latest --help # Docker
brew install cognis-digital/tap/breachwatch # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/breachwatch/main/install.sh | sh
| Linux | macOS | Windows | Docker | Cloud |
|---|---|---|---|---|
scripts/setup-linux.sh | scripts/setup-macos.sh | scripts/setup-windows.ps1 | docker run ghcr.io/cognis-digital/breachwatch | DEPLOY.md (AWS/Azure/GCP/k8s) |
Related Cognis tools
recall— Privacy-first local RAG over personal data — encrypted, audit-loggedoptout— Automated data-broker opt-out engine — top 50 brokers, CCPA/GDPR lettersvaultmap— Personal asset & account inventory — estate-planning-grade encryptedpiicomb— Local PII discovery in your own files — SSN/CC/passport/DL/email/phone/DOBtrackblock— Family phone stalkerware audit — MVT-class iOS/Android forensicsprivacyshell— Hardened browser profile generator — Firefox / LibreWolf / Brave
Explore the suite → 🗂️ all 170+ tools · ⭐ awesome-cognis · 🔗 cognis-sources · 🤖 uncensored-fleet · 🧠 hermes
Contributing
PRs, new rules, and demo scenarios are welcome under the collaboration-pull model — see CONTRIBUTING.md and SECURITY.md.
⭐ If
breachwatchsaved you time, star it — it genuinely helps others find it.
License
Source-available under the Cognis Open Collaboration License (COCL) v1.0 — free for personal, internal-evaluation, research, and educational use; commercial / production use requires a license (licensing@cognis.digital). See LICENSE.