> For the complete documentation index, see [llms.txt](https://docs.ox.security/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ox.security/ox-policies/agentic-pentest.md).

# Agentic Pentest

## Agentic Pentest Policies

Agentic Pentest policies help you identify exploitable vulnerabilities discovered by OX Agentic Pentest.

OX Agentic Pentest uses AI agents to test running web applications the way a real attacker would. It sends real attack payloads, analyzes application responses, and validates whether vulnerabilities are exploitable. This helps security teams focus on confirmed security risks.

### Agentic Pentester

The Agentic Pentester category contains the following policy:

| Policy                | Description                                                                                                                    |
| --------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
| Agentic Pentest Issue | Identifies exploitable vulnerabilities confirmed by OX Agentic Pentest through controlled testing of running web applications. |

### Agentic Pentest Issue

OX Agentic Pentest sends real attack payloads to running applications, analyzes their responses, and confirms which vulnerabilities are exploitable.

Testing covers vulnerabilities such as:

* Broken Object Level Authorization (BOLA)
* Insecure Direct Object References (IDOR)
* Cross-Site Request Forgery (CSRF)
* Business logic flaws
* Multi-step attack chains

Testing runs in a controlled environment to help identify confirmed security issues before attackers exploit them.

#### Policy configuration

| Setting | Description                                         |
| ------- | --------------------------------------------------- |
| On/Off  | Enable or disable the Agentic Pentest Issue policy. |

<br>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.ox.security/ox-policies/agentic-pentest.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
