AI Pentest AgentIt hacks the app, then writes the patch.
Point the agent at a target, set a strict scope, and let it work.
It probes, exploits, saves the request that worked, and opens a fix PR for your review.
Trusted by security teams at
What is an AI pentest agent?
What the agent handles on its own
The agent picks its own next move from whatever the target just told it. It stays inside the scope you set, and every finding and fix comes back to a human for review.
Reads the target
It walks the app, pulls apart the API, and notes every spot where your input reaches a server.
Chooses the next move
A stack trace, an odd redirect, or a slow response will send the agent down a path it had not planned when it started.
Proves the bug
Findings ship with the request and the response that demonstrate them. Anything the agent cannot reproduce stays out of the report.
Writes the patch
The fix arrives as a pull request on your branch for a human to review and merge, and the agent replays its own exploit afterward to see whether it still works.
Calls in more agents
Big targets get a team. A root agent hands subtasks to child agents and keeps a map of what each one turned up.
Stays in its box
Every agent runs inside a sandbox with a strict scope you define, so testing never wanders past the systems you named. Pause it or step in whenever you want.
Where teams point it
The same agent covers the surfaces your team ships to.
Pull requests
Each PR gets an agent pass scoped to the diff before anyone hits merge.
Web apps
Auth flows, session handling, injection, and access control on the running app.
APIs
REST and GraphQL endpoints, including the object-level authorization gaps scanners tend to miss.
Cloud
IAM policy, exposed storage, and workload reachability across AWS, GCP, and Azure.
Internal networks
Hosts behind the VPN, reached through a connector you control.
Your own lab
Practice targets and CTF boxes, which is how a lot of people kick the tires first.
AI pentest agent vs scripted scanner
Both look for bugs. They go about it in ways that produce very different output.
Strix agent
Scripted scanner
Strix agent
Scripted scanner
Strix agent
Scripted scanner
Strix agent
Scripted scanner
Strix agent
Scripted scanner
Strix agent
Scripted scanner
Strix agent
Scripted scanner
Strix agent
Scripted scanner
Strix agent
Scripted scanner
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
What people ask before they run the agent.
Keep exploring
Run the agent on your own target
Install it locally or start hosted. Both take a few minutes.