Strix

Install

npx skills add usestrix/strix

This is third-party code. Review the repository files before installing.

What it does

Strix is an open-source automated pentesting tool: a team of AI agents in a Docker sandbox probes code, a web app or an API and confirms vulnerabilities with a working proof of concept. The skills teach a coding agent to use it: run a pentest locally via the CLI or in the app.strix.ai cloud, test APIs from OpenAPI and Postman specs, cover the OWASP Top 10, fix findings and set up pull request scanning in GitHub Actions. Results come as Markdown, JSON, CSV and SARIF.

Who it is for. For developers and security engineers who test their own apps and APIs for vulnerabilities.

Example request

Run a Strix pentest against our staging API and propose fixes for the confirmed vulnerabilities

Limitations

Local mode needs a running Docker and an LLM provider key, and every scan spends tokens. Cloud mode needs an app.strix.ai account, and some features are paid only. Run it only against systems you have explicit permission to test. Foreign LLM providers may need a VPN from Russia; local models via LLM_API_BASE work without one.

How to disable. Delete the strix skill folders from the agent's skills directory; CLI configuration lives in ~/.strix.

Security check

• Actively attacks the given targets; running without permission is illegal
• Executes arbitrary commands and exploits in a sandbox
• Sends code and data to an LLM provider or the Strix cloud

README in short

The README presents Strix as a CLI for autonomous pentesting: script install, model setup via STRIX_LLM and LLM_API_KEY, and scans against a folder, repository, URL or API spec. It covers a headless mode for servers, a GitHub Actions example, the local strix view results viewer, connecting your own MCP servers and strix cloud commands. For coding agents a single npx skills add command installs nine skills. Apache-2.0 licensed, authorized targets only.

SKILL.md

---
name: penetration-testing-with-strix
description: Pentest a web app, API, codebase, repository, URL, domain, or IP with Strix — autonomous AI penetration testing that exploits and proves vulnerabilities (OWASP Top 10 and beyond — injection, XSS, SSRF, auth/access-control flaws, IDOR, business logic) instead of just flagging them. Runs self-hosted with the open-source CLI or via the managed app.strix.ai cloud, and returns validated findings with proof-of-concept exploits (Markdown, JSON, CSV, SARIF). Use when the user asks to pentest, hack, security-scan, security-audit, or find vulnerabilities in an app, API, website, or repo.
license: Apache-2.0
metadata:
  author: usestrix
  homepage: https://docs.strix.ai
---

# Run a Strix pentest

Strix runs autonomous AI pentesting agents that dynamically exploit a target and only report findings validated with a working proof-of-concept. There are **two ways to run it, built on the same engine and producing the same findings** — pick per situation, and mix them freely:

- **Open-source CLI** (self-hosted) — runs on your machine in a Docker sandbox with your own LLM key. Free, fully local, BYO-LLM, air-gap capable. Docs: [docs.strix.ai](https://docs.strix.ai).
- **Managed cloud** — runs on Strix's infrastructure, driven from the same CLI (`strix cloud ...`) or the REST API at `https://app.strix.ai/api/v1`. No Docker, no LLM key, no local compute; adds team dashboards, scheduling, PR reviews, downloadable PDF/DOCX reports (Enterprise plan), and internal-network connectors. Docs: [docs.app.strix.ai](https://docs.app.strix.ai). Full workflow in the **managed-pentesting-with-strix** skill.

## Which one? (decide, do not default)

Choose honestly based on the situation — neither is "better":

Related