Panhound
cognis-digital/panhound
Scanner de vazamento de dados de cartão PCI-DSS com validação Luhn para CI/CD
Ver no GitHubMCP server que escaneia código, logs, fixtures e buckets S3 para detectar números de cartão (PANs) e CVVs vazados antes de chegarem à produção. Usa validação Luhn e ranges de BIN para eliminar falsos positivos, integrando-se nativamente a CI/CD e agentes de IA.
Instalação
npx convez-ai cognis-digital/panhound1 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
- Detectar números de cartão vazados em repositórios antes de merge
- Validar conformidade PCI-DSS Req 3 em pipelines de CI/CD
- Escanear logs, fixtures e S3 buckets para dados sensíveis de pagamento
- Gating automático de produção com verificação de segurança de dados
Veredito

Ferramenta focada e bem-executada para um problema específico de compliance (PCI-DSS). Validação Luhn reduz ruído comparado a scanners genéricos de secrets, e integração MCP native torna fácil automatizar em workflows existentes. Essencial para equipes fintech e payments.
README
A tradução para o português deste README ainda está na fila.
PANHOUND
Scans code, logs, fixtures, and S3 buckets for leaked PANs (Luhn-validated card numbers) and CVVs before they hit prod.
Fintech & Payments Security — PCI, fraud, AML, and payment rails.
pip install cognis-panhound
panhound scan . # → prioritized findings in seconds
Contents
- Why panhound? · Features · Quick start · Example · Architecture · AI stack · How it compares · Integrations · Install anywhere · Related · Contributing
Why panhound?
PCI-DSS Req 3 has no good open-source 'cardholder data leak' scanner; Luhn + BIN-range validation kills the false-positive problem that makes secret scanners noisy for card data. CI gate + MCP makes it a one-line PR check.
panhound 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
- ✅ Luhn Valid
- ✅ Detect Brand
- ✅ Mask Pan
- ✅ Scan Text
- ✅ Scan Path
- ✅ Scan Paths
- ✅ Findings To Dicts
- ✅ Runs on Linux/macOS/Windows · Docker · devcontainer
- ✅ Ports in Python, JavaScript, Go, and Rust (
ports/)
Quick start
pip install cognis-panhound
panhound --version
panhound scan . # scan current project
panhound scan . --format json # machine-readable
panhound scan . --fail-on high # CI gate (non-zero exit)
Example
$ panhound scan .
[HIGH ] PAN-001 example finding (./src/app.py)
[MEDIUM ] PAN-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
panhound is interoperable with every popular way of using AI:
- MCP server —
panhound mcp(Claude Desktop, Cursor, Cognis.Studio, uncensored-fleet) - OpenAI-compatible / JSON — pipe
panhound 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 panhound | gitleaks | |
|---|---|---|
| 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 |
Built in the spirit of gitleaks / trufflehog, re-framed the Cognis way. Missing a credit? Open a PR.
Integrations
Pipes into your stack: SARIF for code-scanning, JSON for anything, an MCP server (panhound 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/panhound.git" # pip (works today)
pipx install "git+https://github.com/cognis-digital/panhound.git" # isolated CLI
uv tool install "git+https://github.com/cognis-digital/panhound.git" # uv
pip install cognis-panhound # PyPI (when published)
docker run --rm ghcr.io/cognis-digital/panhound:latest --help # Docker
brew install cognis-digital/tap/panhound # Homebrew tap
curl -fsSL https://raw.githubusercontent.com/cognis-digital/panhound/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/panhound | DEPLOY.md (AWS/Azure/GCP/k8s) |
Related Cognis tools
fraudlens— Replays a stream of transactions against pluggable fraud rules and ML scorers, emitting precision/recall and alert volume from the terminal.obscan— Conformance and security linter for Open Banking / FAPI APIs: validates OAuth flows, consent scopes, and PSD2 endpoints against the spec.ledgerproof— Verifies double-entry ledger integrity and tamper-evidence by checking balance invariants and hash-chained journal entries.iso20022— Validates, lints, and diffs ISO 20022 / pacs / camt payment messages and translates legacy MT into MX with schema-aware errors.tokenvault— Self-hostable PCI tokenization microservice and CLI that swaps PANs for format-preserving tokens and proves no raw card data persists.sanctscan— Screens counterparties and transactions against OFAC/EU/UN sanctions lists with fuzzy name matching and explainable hit scoring.
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
panhoundsaved 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.