ViperClaw MCP Server
README.md
<div align="center">
<img src="assets/banner.svg" alt="ViperClaw — AI Pentesting Framework, Bug Bounty Automation MCP Server, Multi-Language SAST Taint Analyzer, and 64 Security Audit Skills for Google Antigravity, Claude Code, OpenAI Codex, and Cursor" width="100%" />
<p align="center">
<a href="https://github.com/zahidoverflow/viperclaw/releases"><img src="https://img.shields.io/github/v/release/zahidoverflow/viperclaw?style=flat-square&logo=github&color=10b981&label=Release" alt="Latest GitHub Release" /></a>
<a href="https://github.com/zahidoverflow/viperclaw/actions"><img src="https://img.shields.io/github/actions/workflow/status/zahidoverflow/viperclaw/ci.yml?branch=main&style=flat-square&logo=githubactions&logoColor=white&label=CI" alt="GitHub Actions CI Status" /></a>
<a href="https://www.python.org/"><img src="https://img.shields.io/badge/Python-3.10%2B%20%7C%20Zero%20Deps-06b6d4?style=flat-square&logo=python&logoColor=white" alt="Python 3.10+ Zero Dependencies" /></a>
<a href="#-cli--mcp-reference"><img src="https://img.shields.io/badge/MCP-13%20Tools-a855f7?style=flat-square" alt="Model Context Protocol MCP Server" /></a>
<a href="#-security-audit-playbooks"><img src="https://img.shields.io/badge/Skills-64%20%2B%201%20Entrypoint-f43f5e?style=flat-square" alt="64 Security Audit Skills + /viperclaw" /></a>
<a href="https://github.com/zahidoverflow/viperclaw/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-10b981?style=flat-square" alt="MIT License" /></a>
</p>
<p align="center">
<b>ViperClaw</b> (<code>viperclaw</code> / <code>vclaw</code>) upgrades <b>Google Antigravity</b>, <b>Claude Code</b>, <b>OpenAI Codex</b>, and <b>Cursor</b> into a standards-driven Application Security & Architecture Audit platform—combining <b>64 specialized security audit skills + <code>/viperclaw</code></b>, a <b>13-tool Phase-Gated MCP server</b>, a <b>BrowserOS Neo session bridge</b>, a <b>Stigmergic SQLite Assessment Graph</b>, <b>Concurrency / JWT / GraphQL / OOB / SAST / HTTP Posture engines</b>, and a <b>deterministic Evidence Verifier</b> with <b>zero third-party runtime dependencies</b>.
</p>
<p align="center">
<a href="https://zahidoverflow.github.io/viperclaw/"><b>Website</b></a> •
<a href="docs/README.md"><b>User Guide</b></a> •
<a href="#-quickstart"><b>Quickstart</b></a> •
<a href="#-architecture"><b>Architecture</b></a> •
<a href="#-cli--mcp-reference"><b>CLI & MCP</b></a> •
<a href="#-security-audit-playbooks"><b>64 Skills</b></a> •
<a href="#-benchmarks--comparison"><b>Benchmarks</b></a>
</p>
</div>
---
## ⚡ Why ViperClaw?
Most automated AppSec wrappers fail in production: dumping **150+ noisy CLI scanners** into an LLM causes context-window rot and noisy alerts, while monolithic container stacks require **4–6 services and separate API budgets** when you already run a frontier coding agent locally.
ViperClaw pairs **64 compliance & code-review playbooks** with **10 zero-dependency Python 3.10+ verification engines** and a strict **"Evidence-First" Quality Gate**:
| Core Subsystem | Capability & Implementation |
| :--- | :--- |
| 🕸️ [**Stigmergic Graph**](src/viperclaw/core/graph.py) | Zero-setup SQLite knowledge graph with priority scoring, decay & Mermaid topology export. |
| 🌐 [**BrowserOS & Posture Inspector**](src/viperclaw/analyzers/browser_bridge.py) | Bridges signed-in **BrowserOS Neo** tabs (`fetch`/`XHR` inspection, JWT claims, storage hygiene) + **non-destructive HTTP/CORS/OpenAPI posture checks**. |
| ⚡ [**Barrier Concurrency Engine**](src/viperclaw/analyzers/race_engine.py) | Pre-connected socket pool synchronized via `threading.Barrier` to verify TOCTOU DB locking & idempotency controls. |
| 🔑 [**JWT & GraphQL Auditors**](src/viperclaw/analyzers/jwt_engine.py) | RFC 8725 JWT claim verification, weak HMAC entropy checks (`alg:none` / `kid` / `RS256`→`HS256`), plus GraphQL schema & batching audits. |
| 📡 [**OOB & JS Harvester**](src/viperclaw/analyzers/oob_engine.py) | HMAC-tagged OOB egress verification canaries + ephemeral callback listener, plus **Webpack / Vite / Next.js** lazy-chunk inventory. |
| 🔬 [**Taint SAST & Oracle**](src/viperclaw/analyzers/taint.py) | Multi-hop taint SAST (**Python, TS/JS, Go, PHP**) + **7-Gate Evidence Verifier** (WAF Soft-200 filter, authorization diff, CVSS 3.1, SARIF 2.1.0). |
---
## 🚀 Quickstart
> 📘 **New to ViperClaw?** Read the complete step-by-step [**Beginner-to-Pro User Guide (`docs/README.md`)**](docs/README.md).
```bash
# 1. Clone & install (<2 seconds, zero external dependencies, Python 3.10+)
git clone https://github.com/zahidoverflow/viperclaw.git
cd viperclaw
pip install -e .
# 2. Install all ViperClaw skills into Antigravity, Claude Code, Codex & Cursor
viperclaw skills install --target all
# 3. Auto-register the Phase-Gated MCP server (e.g. Antigravity ~/.gemini/config/mcp_config.json)
viperclaw mcp install --target antigravity
```
<details>
<summary><b>🔌 Connect the Phase-Gated MCP Server (<code>mcp_config.json</code> / Claude Code / Cursor)</b></summary>
<br />
Run `viperclaw mcp install --target all` (or `claude mcp add viperclaw -- viperclaw mcp`), or add manually to your harness `mcp_config.json` / `.mcp.json`:
```json
{
"mcpServers": {
"viperclaw": {
"command": "viperclaw",
"args": ["mcp"]
}
}
}
```
* **Single-Harness Skill Install:** Use `--target antigravity`, `--target claude`, `--target codex`, or `--target cursor`.
* **Claude Code Plugin Marketplace:** Run `/plugin marketplace add zahidoverflow/viperclaw` then `/plugin install viperclaw@viperclaw`.
</details>
<details>
<summary><b>⚙️ Use in GitHub Actions CI/CD & Pre-Commit Hooks</b></summary>
<br />
**GitHub Actions (`.github/workflows/security.yml`):**
```yaml
- name: Run ViperClaw Security Audit
uses: zahidoverflow/viperclaw@main
with:
path: "."
mode: "taint"
```
**Pre-Commit (`.pre-commit-config.yaml`):**
```yaml
repos:
- repo: https://github.com/zahidoverflow/viperclaw
rev: v2.0.0
hooks:
- id: viperclaw-taint
- id: viperclaw-harvest-js
```
</details>
---
## 🧬 Architecture
<div align="center">
<img src="assets/architecture.svg" alt="ViperClaw 4-Layer Offensive Architecture — AI Coding Harnesses, 64 Security Audit Skills, 13-Tool Phase-Gated MCP Server, Pure-Python Offensive Analyzers, and 7-Gate Proof Oracle" width="100%" />
</div>
---
## 💻 CLI & MCP Reference
Both `viperclaw` and the shorthand `vclaw` alias provide standalone CLI subcommands as well as the JSON-RPC 2.0 `stdio` MCP bridge:
| CLI Command | Purpose & Key Flags |
| :--- | :--- |
| <code>viperclaw scan <url></code> | Stateful live HTTP web scanner & wire-verified exploit runner (`--db`, `--report-md`, `--report-sarif`). |
| <code>viperclaw race <url></code> | Barrier-synchronized concurrent socket burst for TOCTOU race conditions (`-c 20`, `-d`, `--cookie`, `--auth`). |
| <code>viperclaw jwt <token></code> | Decode JWT, crack HMAC secrets, forge `alg:none` / `kid` / `RS256`→`HS256` tokens & replay (`--target-url`). |
| <code>viperclaw graphql <url></code> | Audit GraphQL for introspection bypass, Clairvoyance field suggestions & query batching (`--auth`, `--cookie`). |
| <code>viperclaw oob</code> | Generate HMAC-authenticated blind OOB exploit payloads (SSRF, XXE, CMDi, SSTI, SQLi, JNDI) (`--callback`). |
| <code>viperclaw browser</code> | Output BrowserOS Neo JS runtime hooks (`--scripts`) or ingest a live browser DOM/storage snapshot (`--ingest`). |
| <code>viperclaw taint <path></code> | Multi-language source-to-sink taint SAST for Python, TS/JS, Go & PHP (`--db`, `--output`). |
| <code>viperclaw harvest‑js <path></code> | Webpack / Vite / Next.js lazy-chunk, hidden endpoint & secret harvester (`--base-url`, `--db`, `--output`). |
| <code>viperclaw fingerprint <har></code> | Caido / Burp `.har` backend framework & sibling API fingerprinter (`--domain`, `--output`). |
| <code>viperclaw graph</code> | Query top pheromone-ranked attack leads & export Mermaid topology (`--db`, `--top-leads`, `--mermaid`). |
| <code>viperclaw verify [file]</code> | Run the 7-Question Triage Gate, CVSS 3.1 calculator & H1 MD / SARIF exporter (`--report-md`, `--report-sarif`). |
<details>
<summary><b>📋 View Copy-Paste CLI Workflow Examples (Live DAST, Race Burst, JWT, GraphQL, OOB, SAST)</b></summary>
<br />
```bash
# 1. Run a stateful live web scan & export verified HackerOne Markdown + SARIF 2.1.0
viperclaw scan http://127.0.0.1:4280 --db .viperclaw/graph.db --report-md bounty_report.md --report-sarif findings.sarif
# 2. Fire a 20-worker barrier-synchronized TOCTOU race burst against a coupon/transfer endpoint
viperclaw race https://api.target.tld/v1/coupon/redeem -X POST -d "code=VIPER2026" --cookie "session=abc" -c 20
# 3. Crack a JWT's HMAC secret, synthesize forged admin tokens & replay against a live endpoint
viperclaw jwt "eyJhbGciOiJIUzI1NiIs..." --target-url https://api.target.tld/v1/admin
# 4. Scan a GraphQL endpoint for introspection bypass, Clairvoyance field leaks & batching
viperclaw graphql https://api.target.tld/graphql --auth "Bearer eyJ..."
# 5. Audit source code for multi-hop taint flows & reconstruct SPA lazy chunks
viperclaw taint ./target-repo --db .viperclaw/graph.db --output taint_flows.json
viperclaw harvest-js ./bundles --base-url https://app.target.tld/ --db .viperclaw/graph.db
```
</details>
<details>
<summary><b>🔌 View All 13 Phase-Gated MCP Server Tools (<code>viperclaw mcp</code>)</b></summary>
<br />
| MCP Tool | Phase | Description |
| :--- | :--- | :--- |
| `viper_live_scan` | **Posture** | Run non-destructive HTTP/CORS/header inspection, public API schema discovery, and authorized lab verification. |
| `viper_race_burst` | **Verify** | Verify database locking, idempotency keys, and TOCTOU concurrency controls under synchronized HTTP requests. |
| `viper_jwt_audit` | **Audit** | Audit JWT claims against RFC 8725, verify HMAC secret entropy, and check signature enforcement edge cases. |
| `viper_graphql_scan` | **Audit** | Audit GraphQL for schema introspection exposure, field suggestion hints, array batching & authorization controls. |
| `viper_oob_probe` | **Verify** | Generate HMAC-tagged Out-of-Band (OOB) egress verification canaries and verify callback handling. |
| `viper_browser_ingest` | **BrowserOS** | Output BrowserOS Neo JS runtime telemetry hooks (`fetch`/`XHR`/storage) or ingest browser snapshots into the Graph. |
| `viper_taint_scan` | **SAST** | Run multi-language source-to-sink taint analysis across Python, TypeScript/JavaScript, Go, and PHP. |
| `viper_harvest_js` | **Inventory** | Reconstruct Webpack/Vite/Next.js lazy chunks and inventory endpoints, authorization candidates, GraphQL ops & secrets. |
| `viper_fingerprint_traffic` | **Inventory** | Fingerprint backend frameworks, CDN/WAF banners, CORS posture, and error envelopes from `.har` captures or URLs. |
| `viper_graph_upsert` | **Graph** | Upsert hosts, endpoints, lazy chunks, taint sinks, or findings into the Stigmergic SQLite Assessment Graph. |
| `viper_graph_leads` | **Graph** | Query top pheromone-ranked review leads and export a live Mermaid topology diagram. |
| `viper_diff_oracle` | **Verify** | Compare baseline vs. probe HTTP responses to verify authorization boundaries and filter WAF Soft-200 blocks. |
| `viper_verify_and_report` | **Report** | Run the 7-Question Triage Gate, calculate exact CVSS v3.1 scores, and generate Markdown + SARIF 2.1.0 reports. |
</details>
---
## 🎯 Security Audit Playbooks (64 Skills + `/viperclaw`)
Each skill in [`skills/`](skills/) encodes a senior security engineer's checklist, architecture diagram, and hardened remediation patterns:
* **🧭 Orchestration & QA:** <a href="skills/viperclaw/SKILL.md"><code>/viperclaw</code></a> (Master entrypoint), <a href="skills/viper-orchestrator/SKILL.md"><code>viper‑orchestrator</code></a> (5-Phase Architecture Audit router), and <a href="skills/viper-proof-judge/SKILL.md"><code>viper‑proof‑judge</code></a> (7-Gate Evidence Quality & CVSS 3.1 verifier).
* **🌐 BrowserOS Session & Edge Alignment:** <a href="skills/viper-browseros-agent/SKILL.md"><code>viper‑browseros‑agent</code></a> (BrowserOS Neo DOM & storage audit) and <a href="skills/viper-proxy-parser-alignment/SKILL.md"><code>viper‑proxy‑parser‑alignment</code></a> (reverse-proxy vs. backend parser consistency checks).
* **🔭 Code Inventory & White-Box SAST:** <a href="skills/viper-js-harvester/SKILL.md"><code>viper‑js‑harvester</code></a> (SPA lazy chunks), <a href="skills/viper-proxy-fingerprint/SKILL.md"><code>viper‑proxy‑fingerprint</code></a> (HAR stack profiling), and <a href="skills/viper-taint-sast/SKILL.md"><code>viper‑taint‑sast</code></a> (Polyglot taint auditing).
* **🛡️ Web, API & Cloud Auditing:** <a href="skills/viper-bola-idor/SKILL.md"><code>viper‑bola‑idor</code></a>, <a href="skills/viper-injection-oracle/SKILL.md"><code>viper‑injection‑oracle</code></a>, <a href="skills/viper-ssrf-cloud/SKILL.md"><code>viper‑ssrf‑cloud</code></a>, <a href="skills/viper-auth-oauth-jwt/SKILL.md"><code>viper‑auth‑oauth‑jwt</code></a>, <a href="skills/viper-graphql-ws/SKILL.md"><code>viper‑graphql‑ws</code></a>, and <a href="skills/viper-race-logic/SKILL.md"><code>viper‑race‑logic</code></a>.
* **🤖 AI & MCP Guardrails:** <a href="skills/viper-ai-llm-guardrails/SKILL.md"><code>viper‑ai‑llm‑guardrails</code></a> (Prompt boundaries, MCP authorization & RAG isolation).
<details>
<summary><b>📚 View Full 64-Skill Directory & Methodology Breakdown</b></summary>
<br />
| # | Skill Playbook | Security Audit & Remediation Focus |
| :---: | :--- | :--- |
| `01` | <a href="skills/viper-ai-llm-guardrails/SKILL.md"><code>viper‑ai‑llm‑guardrails</code></a> | AI, LLM & MCP Application Security & Guardrails Auditor (OWASP LLM Top 10). |
| `02` | <a href="skills/viper-auth-oauth-jwt/SKILL.md"><code>viper‑auth‑oauth‑jwt</code></a> | Authentication, OAuth 2.0 / OIDC & JWT Security Auditor. |
| `03` | <a href="skills/viper-aws-iam-cloud-audit/SKILL.md"><code>viper‑aws‑iam‑cloud‑audit</code></a> | AWS IAM, STS, S3, KMS & Lambda Security Auditor (modeled on Prowler, Parliament & CloudSplaining). |
| `04` | <a href="skills/viper-bola-idor/SKILL.md"><code>viper‑bola‑idor</code></a> | Object & Function-Level Authorization (BOLA / BFLA) Audit Skill. |
| `05` | <a href="skills/viper-browser-extension-mv3/SKILL.md"><code>viper‑browser‑extension‑mv3</code></a> | Chrome/Firefox Browser Extension (Manifest V3) Security Auditor. |
| `06` | <a href="skills/viper-browseros-agent/SKILL.md"><code>viper‑browseros‑agent</code></a> | BrowserOS Neo Live Application Inspection & DOM Security Audit Skill. |
| `07` | <a href="skills/viper-cicd-hardening/SKILL.md"><code>viper‑cicd‑hardening</code></a> | CI/CD Pipeline & GitHub Actions Security Auditor (modeled on Zizmor, Actionlint & StepSecurity). |
| `08` | <a href="skills/viper-container-k8s-audit/SKILL.md"><code>viper‑container‑k8s‑audit</code></a> | Docker Container & Kubernetes Manifest Security Auditor (modeled on Trivy, Kubescape & CIS Benchmarks). |
| `09` | <a href="skills/viper-crypto-tls-audit/SKILL.md"><code>viper‑crypto‑tls‑audit</code></a> | Cryptography, Key Management & Password Hashing Auditor (modeled on Trail of Bits & OWASP Cryptographic Storage). |
| `10` | <a href="skills/viper-csrf-samesite-audit/SKILL.md"><code>viper‑csrf‑samesite‑audit</code></a> | Cross-Site Request Forgery (CSRF) Defense & State-Change Auditor (OWASP ASVS V4). |
| `11` | <a href="skills/viper-dependency-sbom/SKILL.md"><code>viper‑dependency‑sbom</code></a> | Software Supply Chain, Lockfile Integrity & Dependency Vulnerability Auditor (modeled on OSV-Scanner, Pip-Audit & Dependabot). |
| `12` | <a href="skills/viper-deserialization-parser/SKILL.md"><code>viper‑deserialization‑parser</code></a> | Safe Deserialization & XML/YAML/JSON Parser Auditor (OWASP Deserialization Cheat Sheet). |
| `13` | <a href="skills/viper-dns-email-domain/SKILL.md"><code>viper‑dns‑email‑domain</code></a> | DNS, Subdomain Takeover, SPF/DKIM/DMARC & Email Security Auditor. |
| `14` | <a href="skills/viper-electron-tauri-desktop/SKILL.md"><code>viper‑electron‑tauri‑desktop</code></a> | Electron & Tauri Desktop Application Security Auditor (modeled on Electronegativity & Doyensec checklists). |
| `15` | <a href="skills/viper-fastapi-django-flask/SKILL.md"><code>viper‑fastapi‑django‑flask</code></a> | Python Web Framework Security Auditor (FastAPI, Django, Flask). |
| `16` | <a href="skills/viper-file-upload-storage/SKILL.md"><code>viper‑file‑upload‑storage</code></a> | File Upload, Path Traversal & Object Storage Security Auditor (OWASP File Upload Cheat Sheet). |
| `17` | <a href="skills/viper-gcp-azure-cloud-audit/SKILL.md"><code>viper‑gcp‑azure‑cloud‑audit</code></a> | Google Cloud (GCP) & Microsoft Azure Security Posture Auditor (modeled on ScoutSuite & Prowler). |
| `18` | <a href="skills/viper-github-repo-governance/SKILL.md"><code>viper‑github‑repo‑governance</code></a> | GitHub Organization, Branch Protection & OpenSSF Scorecard Auditor. |
| `19` | <a href="skills/viper-go-service-audit/SKILL.md"><code>viper‑go‑service‑audit</code></a> | Go (Golang) Microservice & Concurrency Security Auditor (modeled on Trail of Bits Go & gosec). |
| `20` | <a href="skills/viper-graphql-ws/SKILL.md"><code>viper‑graphql‑ws</code></a> | GraphQL Schema & WebSocket Security Auditor. |
| `21` | <a href="skills/viper-grpc-protobuf-audit/SKILL.md"><code>viper‑grpc‑protobuf‑audit</code></a> | gRPC, Protobuf & Internal RPC Security Auditor. |
| `22` | <a href="skills/viper-headers-csp-cors/SKILL.md"><code>viper‑headers‑csp‑cors</code></a> | HTTP Security Headers, Content-Security-Policy (CSP) & CORS Configuration Auditor (modeled on Mozilla Observatory & OWASP Secure Headers). |
| `23` | <a href="skills/viper-iac-terraform-audit/SKILL.md"><code>viper‑iac‑terraform‑audit</code></a> | Infrastructure-as-Code (Terraform, CloudFormation & Pulumi) Security Auditor (modeled on Checkov & tfsec). |
| `24` | <a href="skills/viper-injection-oracle/SKILL.md"><code>viper‑injection‑oracle</code></a> | Input Validation & Query Parameterization Auditor. |
| `25` | <a href="skills/viper-java-spring-audit/SKILL.md"><code>viper‑java‑spring‑audit</code></a> | Java, Spring Boot & Spring Security Auditor (modeled on FindSecBugs & Semgrep Java). |
| `26` | <a href="skills/viper-js-harvester/SKILL.md"><code>viper‑js‑harvester</code></a> | Client-Side Bundle & SPA Manifest Auditor. |
| `27` | <a href="skills/viper-kafka-rabbitmq-queue/SKILL.md"><code>viper‑kafka‑rabbitmq‑queue</code></a> | Event Streaming & Message Queue Security Auditor (Kafka, RabbitMQ, Celery, BullMQ, SQS). |
| `28` | <a href="skills/viper-linux-systemd-host/SKILL.md"><code>viper‑linux‑systemd‑host</code></a> | Linux Host, Systemd Unit, SUID & Seccomp Hardening Auditor (modeled on Lynis & CIS Linux Benchmarks). |
| `29` | <a href="skills/viper-logging-pii-compliance/SKILL.md"><code>viper‑logging‑pii‑compliance</code></a> | Security Logging, PII Redaction & Error Sanitization Auditor (OWASP Logging Cheat Sheet & ASVS V7). |
| `30` | <a href="skills/viper-mcp-server-audit/SKILL.md"><code>viper‑mcp‑server‑audit</code></a> | Model Context Protocol (MCP) Server & Agentic Tool Security Auditor (OWASP MCP Top 10). |
| `31` | <a href="skills/viper-mobile-api-config/SKILL.md"><code>viper‑mobile‑api‑config</code></a> | Mobile App Static Configuration & API Security Auditor (modeled on OWASP MASVS & MobSF). |
| `32` | <a href="skills/viper-multitenant-isolation/SKILL.md"><code>viper‑multitenant‑isolation</code></a> | Multi-Tenant SaaS Data Isolation & Row-Level Security (RLS) Auditor. |
| `33` | <a href="skills/viper-nextjs-react-rsc/SKILL.md"><code>viper‑nextjs‑react‑rsc</code></a> | Next.js App Router, React Server Components & Server Actions Auditor. |
| `34` | <a href="skills/viper-nginx-envoy-gateway/SKILL.md"><code>viper‑nginx‑envoy‑gateway</code></a> | Nginx, Envoy, Traefik & API Gateway Security Auditor (modeled on Gixy & OWASP Reverse Proxy). |
| `35` | <a href="skills/viper-nodejs-express-nestjs/SKILL.md"><code>viper‑nodejs‑express‑nestjs</code></a> | Node.js, Express, NestJS & Fastify Security Auditor. |
| `36` | <a href="skills/viper-oauth-oidc-compliance/SKILL.md"><code>viper‑oauth‑oidc‑compliance</code></a> | OAuth 2.1, OIDC & SSO Protocol Compliance Auditor (RFC 9700). |
| `37` | <a href="skills/viper-openapi-rest-schema/SKILL.md"><code>viper‑openapi‑rest‑schema</code></a> | OpenAPI / Swagger Schema, Mass Assignment & REST API Security Auditor (OWASP API3 & API4). |
| `38` | <a href="skills/viper-orchestrator/SKILL.md"><code>viper‑orchestrator</code></a> | Master 5-Phase Security Audit & Architecture Review Orchestrator. |
| `39` | <a href="skills/viper-payment-stripe-pci/SKILL.md"><code>viper‑payment‑stripe‑pci</code></a> | Payment Processing, Stripe/PayPal Ledger & Financial Precision Auditor. |
| `40` | <a href="skills/viper-php-laravel-wordpress/SKILL.md"><code>viper‑php‑laravel‑wordpress</code></a> | PHP, Laravel & WordPress Security Auditor. |
| `41` | <a href="skills/viper-postgres-redis-mongo/SKILL.md"><code>viper‑postgres‑redis‑mongo</code></a> | Database & Cache Security Auditor (PostgreSQL, Redis, MongoDB). |
| `42` | <a href="skills/viper-privacy-gdpr-hipaa/SKILL.md"><code>viper‑privacy‑gdpr‑hipaa</code></a> | Privacy Engineering, GDPR / HIPAA Data Flow & PII Minimization Auditor. |
| `43` | <a href="skills/viper-proof-judge/SKILL.md"><code>viper‑proof‑judge</code></a> | Evidence Quality Gate, CVSS v3.1 Calculator & Security Report Writer. |
| `44` | <a href="skills/viper-proxy-fingerprint/SKILL.md"><code>viper‑proxy‑fingerprint</code></a> | HTTP Stack, Header & Error-Envelope Auditor. |
| `45` | <a href="skills/viper-race-logic/SKILL.md"><code>viper‑race‑logic</code></a> | Concurrency, Idempotency & Business Logic Auditor. |
| `46` | <a href="skills/viper-rag-vector-audit/SKILL.md"><code>viper‑rag‑vector‑audit</code></a> | RAG Pipeline, Embedding & Vector Database Security Auditor. |
| `47` | <a href="skills/viper-rate-limit-dos-resilience/SKILL.md"><code>viper‑rate‑limit‑dos‑resilience</code></a> | Application Rate Limiting, ReDoS & Resource Exhaustion Auditor (OWASP API4:2023). |
| `48` | <a href="skills/viper-remediation-patch-verifier/SKILL.md"><code>viper‑remediation‑patch‑verifier</code></a> | Security Patch Synthesizer & Regression Test Generator. |
| `49` | <a href="skills/viper-ruby-rails-audit/SKILL.md"><code>viper‑ruby‑rails‑audit</code></a> | Ruby on Rails & Rack Security Auditor (modeled on Brakeman). |
| `50` | <a href="skills/viper-rust-memory-unsafe/SKILL.md"><code>viper‑rust‑memory‑unsafe</code></a> | Rust 'unsafe', FFI, Async & Integer Safety Auditor (modeled on RustSec, Rudra & Clippy security lints). |
| `51` | <a href="skills/viper-saml-sso-enterprise/SKILL.md"><code>viper‑saml‑sso‑enterprise</code></a> | Enterprise SAML 2.0, SCIM & XML Signature Wrapping Auditor. |
| `52` | <a href="skills/viper-sbom-slsa-provenance/SKILL.md"><code>viper‑sbom‑slsa‑provenance</code></a> | SLSA Build Provenance, Sigstore Cosign & Artifact Integrity Auditor. |
| `53` | <a href="skills/viper-secrets-audit/SKILL.md"><code>viper‑secrets‑audit</code></a> | Hardcoded Secret, Credential Entropy & Git History Leak Auditor (modeled on Gitleaks & TruffleHog). |
| `54` | <a href="skills/viper-session-cookie-audit/SKILL.md"><code>viper‑session‑cookie‑audit</code></a> | Session Lifecycle, Cookie Hardening & Token Invalidation Auditor (OWASP ASVS V3). |
| `55` | <a href="skills/viper-smart-contract-review/SKILL.md"><code>viper‑smart‑contract‑review</code></a> | Smart Contract Static Security Auditor (modeled on Slither, Trail of Bits & OpenZeppelin checklists). |
| `56` | <a href="skills/viper-solidity-defi-advanced/SKILL.md"><code>viper‑solidity‑defi‑advanced</code></a> | Advanced DeFi Protocol, Oracle, EIP-712 & Cross-Chain Bridge Auditor (modeled on Trail of Bits, Cyfrin & Immunefi). |
| `57` | <a href="skills/viper-ssrf-cloud/SKILL.md"><code>viper‑ssrf‑cloud</code></a> | Outbound Request (SSRF) & Cloud Egress Auditor. |
| `58` | <a href="skills/viper-taint-sast/SKILL.md"><code>viper‑taint‑sast</code></a> | White-Box Multi-Language Source-to-Sink Taint Analysis Skill. |
| `59` | <a href="skills/viper-threat-model-stride/SKILL.md"><code>viper‑threat‑model‑stride</code></a> | STRIDE Threat Modeling, Data Flow Diagram (DFD) & Trust Boundary Architect (modeled on OWASP Threat Modeling & Trail of Bits). |
| `60` | <a href="skills/viper-proxy-parser-alignment/SKILL.md"><code>viper‑proxy‑parser‑alignment</code></a> | Reverse-Proxy, Edge Filter & Backend Parser Alignment Auditor. |
| `61` | <a href="skills/viper-wasm-c-cpp-memory/SKILL.md"><code>viper‑wasm‑c‑cpp‑memory</code></a> | C, C++, JNI & WebAssembly Memory Safety Auditor (modeled on Trail of Bits C/C++ & Flawfinder). |
| `62` | <a href="skills/viper-webauthn-passkey-mfa/SKILL.md"><code>viper‑webauthn‑passkey‑mfa</code></a> | WebAuthn, FIDO2 Passkey & TOTP MFA Security Auditor. |
| `63` | <a href="skills/viper-webhook-edr-hmac/SKILL.md"><code>viper‑webhook‑edr‑hmac</code></a> | Inbound & Outbound Webhook Security Auditor. |
| `64` | <a href="skills/viper-zero-trust-mtls-mesh/SKILL.md"><code>viper‑zero‑trust‑mtls‑mesh</code></a> | Zero-Trust Service Mesh, Istio/Linkerd mTLS & SPIFFE/SPIRE Auditor. |
</details>
---
## 🏆 Benchmarks & Comparison
ViperClaw is continuously validated against **Damn Vulnerable Web Application (DVWA)** and synthetic TOCTOU/JWT/GraphQL/OOB labs across both static source auditing and live wire exploitation:
* **White-Box Taint SAST (`viperclaw taint`):** **19 / 19 (100%)** vulnerable modules detected via transitive taint tracking, with **0 False Positives** on hardened `impossible.php` targets (`PDO::prepare`, `intval`, `is_numeric`, `in_array`, `htmlspecialchars`).
* **Black-Box Live Exploitation (`viperclaw scan` + `race` + `jwt` + `graphql` + `oob`):** **14 / 14 (100%)** DVWA modules plus barrier-synchronized TOCTOU race windows, HMAC JWT cracking, GraphQL Clairvoyance, and OOB callbacks verified over the wire.
<details>
<summary><b>🔬 View All 14 Wire-Verified DVWA Exploitation Proofs & CVSS v3.1 Vectors</b></summary>
<br />
| # | Severity | Vulnerability Module | Verified Wire Proof / Exploit Vector |
| :---: | :---: | :--- | :--- |
| `01` | **HIGH (8.8)** | OS Command Injection | `ip=127.0.0.1;id` → Verified `uid=33(www-data)` execution |
| `02` | **HIGH (8.1)** | UNION SQL Injection | `' UNION SELECT user,password FROM users#` → Credential hash dump |
| `03` | **MED (6.5)** | Boolean Blind SQLi | True (`1' AND 1=1#`) vs. False (`1' AND 1=2#`) differential oracle |
| `04` | **HIGH (8.1)** | SQLi Auth Bypass | `username=admin' OR '1'='1' LIMIT 1#` → Authenticated admin session |
| `05` | **HIGH (7.1)** | Local File Inclusion | `?page=/etc/passwd` → Verified `root:x:0:0:root:/root:/bin/bash` |
| `06` | **CRIT (9.9)** | Unrestricted Upload RCE | Multipart PHP upload → Verified RCE at `/hackable/uploads/viperclaw_poc.php` |
| `07` | **MED (6.1)** | Reflected XSS | Unescaped HTML payload reflection verified in DOM response |
| `08` | **MED (5.4)** | Stored XSS (Guestbook) | Persistent payload stored in `mtxMessage` and rendered to viewers |
| `09` | **HIGH (8.2)** | Predictable Session ID | Sequential `dvwaSession` $+1$ increment proven across consecutive requests |
| `10` | **HIGH (8.8)** | CSRF Password Reset | State-changing `GET` password reset verified without anti-CSRF token |
| `11` | **MED (6.5)** | CAPTCHA Workflow Bypass | Direct `step=2` state-machine jump verified via auth oracle & restored |
| `12` | **MED (5.4)** | CSP Bypass & Injection | External script injection via permissive `Content-Security-Policy` & `include` |
| `13` | **MED (6.5)** | JS Token Reversal | Reversed `md5(rot13("success"))` client-side token & verified acceptance |
| `14` | **MED (6.1)** | DOM-Based XSS | Unescaped `location.href` sink into `document.write()` verified in browser |
</details>
<details>
<summary><b>📊 View 2026 AI Pentesting Framework Comparison Matrix (ViperClaw v2.0 vs. Strix, PentAGI, HexStrike, Vulnhuntr)</b></summary>
<br />
| Capability / Architecture | 🐍 ViperClaw v2.0 | Strix / Shannon | PentAGI / RedAmon | HexStrike AI | Vulnhuntr |
| :--- | :---: | :---: | :---: | :---: | :---: |
| **Architecture Pattern** | **64 Skills + 13 MCP + Engine** | Containerized Agent | Docker + Neo4j Stack | 150-Tool MCP | Python AST CLI |
| **Native Inside Antigravity / Claude / Codex / Cursor** | ✅ **Native** | ⚠️ CLI Wrapper | ⚠️ Partial | ✅ MCP Only | ❌ Standalone |
| **Signed-In BrowserOS Neo DOM & Fetch Bridge** | ✅ **Built-in** | ⚠️ Isolated Container | ❌ | ❌ | ❌ |
| **Barrier-Synchronized Socket Race Engine** | ✅ **Built-in** | ❌ | ❌ | ❌ | ❌ |
| **JWT Cracker + Forger & GraphQL Clairvoyance** | ✅ **Built-in** | ⚠️ Partial | ❌ | ⚠️ External CLI | ❌ |
| **Cryptographic OOB Canary & Ephemeral Listener** | ✅ **Built-in** | ✅ OOB | ⚠️ Partial | ❌ | ❌ |
| **Zero-Setup SQLite Attack Graph + Mermaid** | ✅ **Built-in** | ❌ | ⚠️ Needs Neo4j/PG | ❌ | ❌ |
| **SPA Lazy-Chunk Reconstruction (Webpack/Vite/Next)** | ✅ **Built-in** | ⚠️ Partial | ❌ | ❌ | ❌ |
| **Multi-Language White-Box Taint SAST** | ✅ **Py / TS / Go / PHP** | ✅ Dynamic + Code | ❌ Black-Box | ❌ | ⚠️ **Py 3.10 Only** |
| **Deterministic WAF Soft-200 & BOLA Diff Oracle** | ✅ **Built-in** | ✅ PoC Validation | ⚠️ LLM-Judged | ❌ Raw Stdout | ❌ Static Only |
| **Runtime Dependencies** | ✅ **0 (Pure Stdlib)** | Docker + Node/LLM | Docker + DB + Kali | 150+ CLI Tools | Python 3.10 + `jedi` |
</details>
<details>
<summary><b>📂 View Repository Structure & Package Layout</b></summary>
<br />
```text
viperclaw/
├── .claude-plugin/ # Claude Code Marketplace & Plugin manifests
├── .github/workflows/ci.yml # GitHub Actions CI matrix (Python 3.10, 3.11, 3.12)
├── assets/ # Custom Light-Theme SVG Banner & Architecture Diagrams
├── docs/README.md # Beginner-to-Pro Complete Usage & Best-Utilization Guide
├── logo.png # Lightweight 512x512 transparent square emblem
├── skills/ # 14 Methodology-Driven Offensive Skills (SKILL.md)
├── src/viperclaw/ # Zero-Dependency Python 3.10+ Core Package
│ ├── cli.py # CLI entrypoints (`viperclaw` & `vclaw`)
│ ├── mcp_server.py # Phase-Gated 13-Tool JSON-RPC 2.0 stdio MCP Server
│ ├── core/ # Stigmergic Attack Graph, Proof Oracle & SARIF Reporter
│ └── analyzers/ # Live DAST, Race, JWT, GraphQL, OOB, BrowserOS, Taint, JS & HAR
├── tests/test_viperclaw.py # 11 End-to-End & Adversarial QA Regression Suites
├── CITATION.cff # Academic & Research Citation Metadata
├── glama.json # MCP Registry Manifest
├── llms.txt # AI / LLM Context Discovery Index
└── pyproject.toml # PEP 621 Zero-Dependency Package Configuration
```
</details>
<details>
<summary><b>❓ Frequently Asked Questions (FAQ)</b></summary>
<br />
* **Why use ViperClaw instead of a standalone Docker security stack?**
If you already use **Google Antigravity**, **Claude Code**, **OpenAI Codex**, or **Cursor**, spinning up a separate 5-container Docker stack with its own LLM API billing is redundant. ViperClaw installs in 2 seconds with zero dependencies and turns your existing coding agent into an evidence-gated AppSec & architecture audit platform.
* **How does ViperClaw prevent AI hallucinations and WAF "Soft-200" false positives?**
Generic AI wrappers often report `200 OK` HTML challenge pages from **Cloudflare, Akamai, Imperva, or CloudFront** as vulnerabilities. ViperClaw's [`ProofOracle`](src/viperclaw/core/oracle.py) filters WAF soft-blocks, diffs structural JSON keys for BOLA/IDOR, and enforces a strict **7-Question Pre-Submission Gate** (*"No Receipt, No Report"*).
* **How do I run the regression test suite?**
Run `pytest -v` from the repository root to execute all 11 end-to-end and adversarial QA test suites.
</details>
---
## 📜 Documentation, Security & License
* 📘 **Full User Guide:** [**`docs/README.md`**](docs/README.md) • 🌐 **Website:** [**zahidoverflow.github.io/viperclaw**](https://zahidoverflow.github.io/viperclaw/)
* 🤝 **Contributing & Security Policy:** Review [**`CONTRIBUTING.md`**](CONTRIBUTING.md) and [**`SECURITY.md`**](SECURITY.md).
* ⚠️ **Authorized Use Only:** Developed strictly for authorized security assessments, bug bounty programs with explicit scope permission, educational labs (DVWA / HTB / CTFs), and defensive code auditing.
* ⚖️ **License:** [**MIT License**](LICENSE) — Created by **Zahidul Islam ([@zahidoverflow](https://github.com/zahidoverflow))**.
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues