{ "markdown": "

\n \n \"Strix\n \n

\n\n
\n\n# Strix\n\n### The open-source AI pentesting tool. Autonomous AI hackers that find and fix your app’s vulnerabilities.\n\n
\n\n\n\"Docs\"\n\"Website\"\n[![](https://dcbadge.limes.pink/api/server/strix-ai)](https://discord.gg/strix-ai)\n\n\"Strix\n\"Try\n\n\"Ask\n\"GitHub\n\"License\"\n\"PyPI\n\n\n\"Join\n\"Follow\n\n\n\"usestrix%2Fstrix\n\"usestrix/strix\n\n
\n\n\n> [!TIP]\n> **New!** Strix integrates seamlessly with GitHub Actions and CI/CD pipelines. Automatically scan for vulnerabilities on every pull request and block insecure code before it reaches production - [Get started with no setup required](https://app.strix.ai?utm_source=github&utm_medium=readme&utm_content=tip_ci).\n\n---\n\n\n## Strix Overview\n\nStrix are autonomous AI penetration testing agents that act just like real hackers - they run your code dynamically, find vulnerabilities, and validate them through actual proofs-of-concept. Built for developers and security teams who need fast, accurate security testing without the overhead of manual pentesting or the false positives of static analysis tools.\n\n**Key Capabilities:**\n\n- **Full pentesting toolkit** - reconnaissance, exploitation, and validation out of the box\n- **Multi-agent orchestration** - teams of AI pentesters that collaborate and scale\n- **Real exploit validation** - working PoCs, not false positives like legacy vulnerability scanners\n- **Developer‑first CLI** - actionable findings with remediation guidance\n- **Auto‑fix & reporting** - generate patches and compliance-ready pentest reports\n\n\n
\n\n\n
\n \n \"Strix\n \n
\n\n\n## Use Cases\n\n- **Application Security Testing** - Detect and validate critical vulnerabilities in your applications\n- **Rapid Penetration Testing** - Get penetration tests done in hours, not weeks, with compliance reports\n- **Bug Bounty Automation** - Automate bug bounty research and generate PoCs for faster reporting\n- **CI/CD Integration** - Run tests in CI/CD to block vulnerabilities before reaching production\n\n## 🚀 Quick Start\n\n**Prerequisites:**\n- Docker (running)\n- An LLM API key from any [supported provider](https://docs.strix.ai/llm-providers/overview) (OpenAI, Anthropic, Google, etc.)\n\n### Installation & First Scan\n\n```bash\n# Install Strix\ncurl -sSL https://strix.ai/install | bash\n\n# Configure your AI provider\nexport STRIX_LLM=\"openrouter/z-ai/glm-5.3\"\nexport LLM_API_KEY=\"your-api-key\"\n\n# Run your first security assessment\nstrix --target ./app-directory\n```\n\n> [!NOTE]\n> First run automatically pulls the sandbox Docker image. Results are saved to `strix_runs/`\n\n---\n\n## Ways to Run Strix\n\n- **Open Source** - free, runs locally with Docker and your own LLM key. [Quick Start](https://docs.strix.ai/quickstart)\n- **Strix Cloud** - no setup, validated findings, one-click autofix, and PR reviews. [Run a pentest →](https://app.strix.ai?intent=pentest&utm_source=github&utm_medium=readme&utm_content=table_cloud)\n- **Enterprise** - SSO, compliance-ready reports, VPC or self-hosted deployment. [Try Strix Enterprise →](https://strix.ai/demo?utm_source=github&utm_medium=readme&utm_content=table_demo)\n\n---\n\n## ☁️ Strix Cloud\n\nTry the Strix full-stack penetration testing platform at **[app.strix.ai](https://app.strix.ai?utm_source=github&utm_medium=readme&utm_content=cloud_heading)** - sign up for free, connect your repos and domains, and launch a pentest in minutes.\n\n- **Validated findings with PoCs** - every vulnerability includes a working proof-of-concept exploit and reproduction steps\n- **One-click autofix** - AI-generated security patches as ready-to-merge pull requests\n- **Continuous pentesting** - always-on vulnerability scanning that keeps pace with your deployments\n- **DevSecOps integrations** - GitHub, GitLab, Bitbucket, Slack, Jira, Linear, and CI/CD pipelines\n- **Continuous learning** - AI that builds on past findings, adapts to your codebase, and reduces false positives over time\n\n[**Run a pentest →**](https://app.strix.ai?intent=pentest&utm_source=github&utm_medium=readme&utm_content=cloud_cta)\n\n## 🏢 Enterprise\n\nGet the same Strix experience with enterprise-grade controls: SSO (SAML/OIDC), custom compliance-ready penetration testing reports (SOC 2, ISO 27001, PCI DSS), dedicated support and SLA, custom deployment options (VPC or self-hosted), BYOK model support, and tailored AI pentesting agents optimized for your environment.\n\n[**Try Strix Enterprise →**](https://strix.ai/demo?utm_source=github&utm_medium=readme&utm_content=enterprise_cta)\n\n---\n\n## 🤖 Use Strix from Your Coding Agent\n\nStrix is agent-ready. Give Claude Code, Cursor, Codex, or any [SKILL.md-compatible](https://agentskills.io) agent the ability to run pentests, fix findings, and set up CI scanning:\n\n```bash\nnpx skills add usestrix/strix\n```\n\nThis installs nine skills for running pentests, fixing findings, and CI scanning, against code, web apps, APIs, and the OWASP Top 10. Agents can use the local CLI or the managed cloud with the same engine.\n\nSee [`AGENTS.md`](AGENTS.md) for the quick reference, [docs.strix.ai/llms.txt](https://docs.strix.ai/llms.txt) for the CLI, and [docs.app.strix.ai](https://docs.app.strix.ai) for the API.\n\n---\n\n## ✨ Features\n\n### Agentic Pentesting Tools\n\nStrix agents come equipped with a comprehensive offensive security toolkit - the same tools used by professional penetration testers and ethical hackers:\n\n- **HTTP Interception Proxy** - Full request/response manipulation and analysis with Caido\n- **Browser Exploitation** - Automated browser for testing XSS, CSRF, clickjacking, and auth bypass flows\n- **Shell & Command Execution** - Interactive terminal for exploit development and post-exploitation\n- **Custom Exploit Runtime** - Python sandbox for writing and validating proof-of-concept exploits\n- **Reconnaissance & OSINT** - Automated attack surface mapping, subdomain enumeration, and fingerprinting\n- **Static & Dynamic Code Analysis** - SAST + DAST capabilities for comprehensive application security testing\n- **Vulnerability Knowledge Base** - Structured findings with CVSS scoring and OWASP classification\n\n### Comprehensive Vulnerability Scanner\n\nStrix identifies, validates, and exploits a wide range of security vulnerabilities across the OWASP Top 10 and beyond:\n\n- **Broken Access Control** - IDOR, privilege escalation, auth bypass\n- **Injection Attacks** - SQL injection, NoSQL injection, OS command injection, SSTI\n- **Server-Side Vulnerabilities** - SSRF, XXE, insecure deserialization, RCE\n- **Client-Side Attacks** - XSS (stored/reflected/DOM), prototype pollution, CSRF\n- **Business Logic Flaws** - Race conditions, payment manipulation, workflow bypass\n- **Authentication & Session** - JWT attacks, session fixation, credential stuffing vectors\n- **Infrastructure & Cloud** - Misconfigurations, exposed services, cloud security issues\n- **API Security** - Broken authentication, mass assignment, rate limiting bypass\n\n### Graph of Agents (Multi-Agent Pentesting)\n\nAdvanced multi-agent orchestration for comprehensive automated penetration testing:\n\n- **Distributed Pentesting** - Specialized AI agents for recon, exploitation, and post-exploitation\n- **Scalable Security Testing** - Parallel execution across multiple targets for fast, comprehensive coverage\n- **Dynamic Coordination** - Agents share discoveries, chain vulnerabilities, and collaborate like a red team\n\n---\n\n## 🖥️ Local Web Viewer\n\nEvery scan writes its results to disk as it runs. Bring them up in a local dashboard with a single command:\n\n```bash\n# Open the most recent run\nstrix view\n\n# ...or open a specific run by name\nstrix view my-run-name\n\n# Expose the viewer on all IPv4 interfaces at a fixed port\nstrix view --host 0.0.0.0 --port 8080 --no-open\n```\n\nThe dashboard shows the findings, a live map of the agent team, and past runs. Nothing leaves your machine, and the UI ships prebuilt. `strix view` binds to `127.0.0.1` and prints a tokened link that grants access to the run, so share it carefully.\n\nSee the [viewer documentation](https://docs.strix.ai/usage/viewer) for the options and for reaching the viewer from another machine.\n\n---\n\n## Usage Examples\n\n### Basic Usage\n\n```bash\n# Scan a local codebase\nstrix --target ./app-directory\n\n# Security review of a GitHub repository\nstrix --target https://github.com/org/repo\n\n# Black-box web application assessment\nstrix --target https://your-app.com\n```\n\n### API Testing (OpenAPI / Swagger / Postman)\n\nPoint Strix at an API contract and it tests every declared endpoint instead of\nhaving to discover them by crawling. Pair the spec with the live base URL so the\nagent knows where to send traffic:\n\n```bash\n# OpenAPI / Swagger file, Postman export, or a live collection by id\nstrix --target ./openapi.yaml --target https://api.your-app.com\nstrix --target postman:// --target https://api.your-app.com\n```\n\n\n### Advanced Testing Scenarios\n\n```bash\n# Grey-box authenticated testing\nstrix --target https://your-app.com --instruction \"Perform authenticated testing using credentials: user:pass\"\n\n# Multi-target testing (source code + deployed app)\nstrix -t https://github.com/org/app -t https://your-app.com\n\n# Targets from a file, one target per non-empty, non-comment line\nstrix --target-list ./targets.txt\n```\n\nSee the [CLI reference](https://docs.strix.ai/usage/cli) for every option, including scan modes, diff scope, instruction files, and budgets.\n\n### Headless Mode\n\nRun Strix programmatically without interactive UI using the `-n/--non-interactive` flag - perfect for servers and automated jobs. The CLI prints real-time vulnerability findings and the final report before exiting. Exits with non-zero code when vulnerabilities are found.\n\n```bash\nstrix -n --target https://your-app.com\n```\n\n### CI/CD (GitHub Actions)\n\nStrix can be added to your pipeline to run a security test on pull requests with a lightweight GitHub Actions workflow:\n\n```yaml\nname: strix-penetration-test\n\non:\n pull_request:\n\njobs:\n security-scan:\n runs-on: ubuntu-latest\n steps:\n - uses: actions/checkout@v6\n with:\n fetch-depth: 0\n\n - name: Install Strix\n run: curl -sSL https://strix.ai/install | bash\n\n - name: Run Strix\n env:\n STRIX_LLM: ${{ secrets.STRIX_LLM }}\n LLM_API_KEY: ${{ secrets.LLM_API_KEY }}\n\n run: strix -n -t ./ --scan-mode quick\n```\n\n> [!TIP]\n> In CI pull request runs, Strix automatically scopes quick reviews to changed files, which is why the\n> checkout above fetches full history. See the\n> [CI/CD documentation](https://docs.strix.ai/integrations/github-actions) for the details.\n\n### Configuration\n\n```bash\nexport STRIX_LLM=\"openrouter/z-ai/glm-5.3\"\nexport LLM_API_KEY=\"your-api-key\"\n\n# Optional\nexport LLM_API_BASE=\"your-api-base-url\" # if using a local model, e.g. Ollama, LMStudio\n```\n\n> [!NOTE]\n> Strix automatically saves your configuration to `~/.strix/cli-config.json`, so you don't have to re-enter it on every run.\n> See the [configuration reference](https://docs.strix.ai/advanced/configuration) for every environment variable.\n\n#### Sign in with a ChatGPT subscription\n\nInstead of a metered API key, you can run Strix on your ChatGPT Plus/Pro subscription:\n\n```bash\nstrix auth login chatgpt # sign in with your ChatGPT account\nexport STRIX_LLM=\"chatgpt/gpt-5.4\" # chatgpt/ runs on the subscription\nstrix auth status # show the active sign-in, or logout to forget it\n```\n\n#### Use the managed platform: `strix cloud`\n\nRun scans on [app.strix.ai](https://app.strix.ai) from the terminal, without Docker or an LLM key:\n\n```bash\nstrix cloud login # browser sign-in, one credential per install\nstrix cloud scans start --source . --yes --wait # scan local code, approving the upload\nstrix cloud scans start --engagement-type live_test --domain-ids --wait\nstrix cloud vulns list --severity critical\n```\n\nEvery [REST API](https://docs.app.strix.ai) operation has a matching `strix cloud ` command. Run `strix cloud` to list the resources, and add `help` to a resource to list its verbs. Output is JSON when stdout is not a terminal or when you pass `--json`. Binary downloads are the exception: redirect the raw bytes, or combine `--output FILE --json` for download metadata.\n\nSee the [cloud CLI documentation](https://docs.strix.ai/cloud/cli) for scopes, workspaces, billing, and source-upload options.\n\n#### Connect your own MCP servers\n\nStrix can connect to Model Context Protocol (MCP) servers you list and expose their tools to the agent during a run. Create `~/.strix/mcp-servers.json` with a JSON list of local `stdio` servers or remote `http` servers:\n\n```json\n[\n {\n \"name\": \"github\",\n \"transport\": \"http\",\n \"url\": \"https://api.githubcopilot.com/mcp/\",\n \"auth\": { \"kind\": \"bearer\", \"token\": \"your-token\" },\n \"allowed_tools\": [\"list_issues\"]\n }\n]\n```\n\nEach server's tools are namespaced by `name`, for example `github_list_issues`. See the [MCP documentation](https://docs.strix.ai/integrations/mcp) for the full schema, tool filtering, and `stdio` servers.\n\n**Recommended models for best results:**\n\n- [Z.ai GLM-5.3 on OpenRouter](https://openrouter.ai/z-ai/glm-5.3) - `openrouter/z-ai/glm-5.3` (the default pick)\n- [OpenAI GPT-5.4](https://openai.com/api/) - `openai/gpt-5.4`\n- [Anthropic Claude Sonnet 4.6](https://claude.com/platform/api) - `anthropic/claude-sonnet-4-6`\n- [Google Gemini 3 Pro Preview](https://cloud.google.com/vertex-ai) - `vertex_ai/gemini-3-pro-preview`\n- [DeepSeek V4 Pro](https://platform.deepseek.com) - `deepseek/deepseek-v4-pro`\n- [Moonshot Kimi K3](https://platform.kimi.ai) - `moonshot/kimi-k3`\n\nSee the [LLM Providers documentation](https://docs.strix.ai/llm-providers/overview) for all supported providers including Vertex AI, Bedrock, Azure, and local models.\n\n## Documentation\n\nFull documentation is available at **[docs.strix.ai](https://docs.strix.ai)** - including detailed guides for usage, CI/CD integrations, skills, and advanced configuration.\n\n## Contributing\n\nWe welcome contributions of code, docs, and new skills - check out our [Contributing Guide](https://docs.strix.ai/contributing) to get started or open a [pull request](https://github.com/usestrix/strix/pulls)/[issue](https://github.com/usestrix/strix/issues).\n\n## Join Our Community\n\nHave questions? Found a bug? Want to contribute? **[Join our Discord!](https://discord.gg/strix-ai)**\n\n## Support the Project\n\n**Love Strix?** Give us a ⭐ on GitHub!\n\n## Acknowledgements\n\nStrix builds on the incredible work of open-source projects like [LiteLLM](https://github.com/BerriAI/litellm), [Caido](https://github.com/caido/caido), [Nuclei](https://github.com/projectdiscovery/nuclei), [Playwright](https://github.com/microsoft/playwright), and [Bubble Tea](https://github.com/charmbracelet/bubbletea). Huge thanks to their maintainers!\n\n\n> [!WARNING]\n> **Authorized use only.** Strix actively tests the targets you point it at, so only run it against systems you own or have **explicit, written permission** to test, and stay within the agreed scope. Unauthorized testing is illegal in most jurisdictions.\n> You alone are responsible for obtaining authorization and complying with the law. Strix is provided \"as is\" with no warranty or liability for misuse.\n\n\n", "bytes": 17574, "sha": "f6d5cf80126692cfb86589df9f1cf4fb11dc605c014247374f0e4dda1d741fa0", "repo_slug": "usestrix/strix", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/skl_usestrix_strix_api_security_testing_1a363253/readme" }