Open Source PentestingRead the code, run the agent, keep the data.
Strix is a Python package with an Apache-2.0 license and more than 50,000 stars on GitHub.
It runs on your hardware, against your targets, with whatever model you choose.
Trusted by security teams at
What open source pentesting looks like here
Why teams pick the self-hosted route
Source code and traffic tend to be the two things a security team refuses to hand over.
One command to start
pip install strix-agent, then point it at a repo or a URL. First run takes about a minute.
Any model you like
OpenAI, Anthropic, Google, Bedrock, Vertex, OpenRouter, or a local model served through Ollama or vLLM.
Works air-gapped
With a local model and a local target, the agent never opens an outbound connection.
Auditable by design
The prompts and skill files are plain markdown in the repo. Read what the agent was told before you trust what it did.
Extend it
Add a skill file and the agent picks up your house methodology, your payloads, and your internal tooling.
An active project
Over 50,000 stars, 5,000 forks, and a Discord where people post what they broke this week.
What ships in the repo
The parts that would otherwise be someone else's black box.
The agent runtime
Task loop, memory compression, and the graph that lets one agent spawn others.
The tool belt
Shell, browser driver, HTTP proxy, and the code search the agent uses to read your repo.
Skills
Markdown playbooks for SSRF, IDOR, auth bypass, and the rest of the catalog.
The sandbox
A Kali-based container image with the blast radius already fenced off.
Human in the loop
Chat with the agent mid-run to steer it toward a suspicious endpoint, hand it credentials, or ask why it took a path.
BYO credentials
Your model keys stay in your environment. Nothing routes through a vendor.
Self-hosted agent vs vendor cloud
Where your code sits during a test changes what a security review has to cover.
Strix, self-hosted
Typical SaaS pentest tool
Strix, self-hosted
Typical SaaS pentest tool
Strix, self-hosted
Typical SaaS pentest tool
Strix, self-hosted
Typical SaaS pentest tool
Strix, self-hosted
Typical SaaS pentest tool
Strix, self-hosted
Typical SaaS pentest tool
Strix, self-hosted
Typical SaaS pentest tool
Strix, self-hosted
Typical SaaS pentest tool
From issue to fix in seconds
Find critical issues, auto-validate, and auto-fix with merge-ready PRs.
SSRF via URL Parameter in /api/proxy
TL;DR
The /api/proxy endpoint accepts a user-supplied URL without validation. An attacker can access internal services, read cloud metadata, and exfiltrate credentials.
Impact
Access to cloud metadata at 169.254.169.254, potential credential theft, and internal network scanning.
Location
acme/api · proxy-handler.ts:23Severity
CVSS
8.6Fix Effort
LowDiscovered
2h agoDiscover & Validate
Pentests your entire attack surface continuously. Reproduces each finding, confirms exploitability with proof, and prioritizes by real impact.
How do I fix it?
Validate and restrict the target URL using an allowlist of permitted hostnames. Reject private/internal IP ranges and enforce HTTPS-only.
| 23 | 23 | const targetUrl = req.query.url; |
| 24 | const resp = await fetch(targetUrl); | |
| 24 | const parsed = new URL(targetUrl); | |
| 25 | if (!ALLOWED_HOSTS.has(parsed.hostname)) { | |
| 26 | throw new ForbiddenError("blocked"); | |
| 27 | } | |
| 28 | const resp = await fetch(parsed.href); | |
| 25 | 29 | return res.json(await resp.json()); |
Auto-Fix
Generates a fix, retests to confirm the vulnerability is gone, and delivers a merge-ready PR. Review, merge, done.
Frequently asked questions
The practical questions about running it yourself.