Strix skill
Nine skills that let an agent run Strix pentests, fix validated findings and add security scanning to CI
- 72,594 ★ on the repository
- Last commit
- Apache-2.0
Broad access
Why this level
- 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
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/strixDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewBroad accessThe tool can change data, run commands or handle secrets.
- 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
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.
Good fit when
- You need to test your own app or API for vulnerabilities before a release
- You want a static analysis finding confirmed by real exploitation
- You want security scanning on pull requests
Not a fit when
- You do not have written permission to test the target
- You have no Docker or LLM key and cannot upload code to the cloud
Example request
Run a Strix pentest against our staging API and propose fixes for the confirmed vulnerabilitiesLimitations
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.
FAQ
How does local mode differ from cloud?
Local runs in your Docker with your own LLM key and keeps code on your machine. Cloud runs via strix cloud commands, needs no Docker or key, and adds dashboards and PR reviews.
Can I use a local model?
Yes, via the LLM_API_BASE variable, for example with Ollama or LM Studio.
Discussion
No questions or reviews yet.
Related
SkillsA pack of about fifty Claude Code subagents for authorized pentesting: planning, recon, exploit research and chaining, post-exploitation, detection and reportin
A CLI agent for authorized pentesting: from a natural-language brief it runs recon, finds and verifies vulnerabilities and prepares a report
A security scanner for agent skills: finds prompt injection, data exfiltration and malicious code before you install
A practical security skills base for agents: web, API, privilege escalation, Active Directory, mobile, binaries and crypto
An autonomous AI pentester that proves every finding: verified bugs ship a proof capsule you can replay
A set of skills for external OSINT recon: methodology, tactical arsenal and deep attack-surface analysis for authorized assessments
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.
README badge
Original 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":