Research Academy My account Customers About Blog Careers Legal Contact Resellers

DASTProfessional

AI trust and data handling

  • Last updated: November 17, 2026

  • Read time: 15 Minutes

This page answers common questions about how Burp AT and the AI features in Burp Suite DAST keep your testing safe, how you stay in control when using AI features, and how PortSwigger handles the data you send.

Data handling

What information is sent to PortSwigger and AI providers?

Burp AT in Burp Suite Professional

Burp AT sends the information the AI needs to reason about your task:

  • Your prompts and any goals you set with /goal.
  • Any resources you send to Burp AT, such as a message from the HTTP history, a node from your site map, or an issue found by the scanner.
  • Files you attach.
  • The agent's own messages.
  • Each tool call the agent makes, and the arguments it passes to that tool.
  • The result each tool returns. For tools that send HTTP requests, this includes the full request and response.
  • Task metadata, such as token counts and the time each request was started.

Burp AT does not upload your Burp project. Its tools run locally in Burp, and Burp returns only the results of the tool calls the agent makes.

PortSwigger stores the conversation as your task runs, and includes it in requests to the AI provider. This enables the agent to keep track of its work. Attachment contents are stored separately and are only sent when Burp AT needs to access the file. For more information on data storage, see What data does PortSwigger store?

Burp AT in Burp Suite enterprise platform

Burp AT sends your objectives, chat messages, and the site's background context to PortSwigger's AI service. The agent also receives the results of the testing tools it calls. These results can include HTTP request and response data from your target.

For example, the request-sending tool returns response headers and body content. It can shorten large responses, and the agent can request more content when needed.

AI-enhanced scanning and AI-recorded login sequences in Burp Suite DAST

  • AI-enhanced scanning: the full HTTP request and response pair in which the issue was found, including headers; the issue name, target URL, and insertion point; and the origin scan ID and site ID.
  • Recorded logins: the page text, HTML attributes of interactive elements, and a screen capture of the page.

What do Explain and Explore send to Burp AT?

These actions create Burp AT tasks and supply context for the task:

  • Clicking Explain selected text sends your selection and its location, without attaching the full message or issue.
  • Clicking Explore request in Burp AT in Repeater sends your prompt and selected context. Burp attaches the selected messages with your notes. If you include notes without a message, then Burp adds them to the prompt. Highlighted text accompanies the attached message and also appears in the prompt. Selecting Response also includes its originating request. If you edit the request, then Burp omits its earlier response.
  • Exploring a Scanner issue sends the issue details and attaches the issue so Burp AT can inspect its evidence.

As the task continues, Burp AT also sends the messages, tool calls, and results listed in What does Burp AT send to PortSwigger and AI providers?.

Do AI features send sensitive data?

Burp AT in Burp Suite Professional

Yes, depending on what you're testing. Requests, responses, attached resources, and attached files may contain sensitive data. Burp AT does not redact this data before sending it to PortSwigger and AI providers.

You can configure what Burp AT can do without approval. If you need to check what leaves your machine, require manual approval before Burp AT sends any request. For more information, see Can Burp AT send destructive requests?

Burp AT in Burp Suite enterprise platform

Yes, depending on what you're testing. Your objectives, chat messages, site context, and HTTP data returned by testing tools may contain sensitive information. Tool results can include response headers, cookies, and body content. Credentials and session tokens may also reach the AI. Recorded-login generation masks specific credentials, but this does not provide general redaction for agentic tests.

AI-enhanced scanning and AI-recorded login sequences in Burp Suite DAST

They can. These AI features do not automatically redact or mask the data sent to AI providers. Depending on the features you use and the traffic you're testing, this may include sensitive data.

As an exception, AI-generated recorded logins replace actual usernames and passwords with placeholders before they are sent to PortSwigger or the AI providers. This is the same behavior as manually-recorded logins.

What data does PortSwigger store?

PortSwigger stores your prompts, AI responses, and associated metadata to support troubleshooting, auditing, billing, and account management. This includes:

  • Any data you send as context, such as highlighted HTTP headers or code snippets.
  • The full conversation for a Burp AT task, including the agent's messages, its tool calls, and the results those tools return.
  • Any resources you send to Burp AT, such as HTTP messages, site map nodes, and scanner issues.
  • Files you attach to a Burp AT task. PortSwigger stores the file contents separately from the conversation. The conversation contains information about the attachment, but not its contents.
  • Task metadata, such as which feature was used, issue details, and target URLs.
  • The timestamp at which the request was started.
  • Your license details, token counts, credit consumption, and request counts.

In the Burp Suite enterprise platform, Burp AT also saves a Burp project for each agentic test. It uses this project to restore the test's work when its hosted environment restarts.

How long is my data retained?

We retain different types of data to operate, support, and improve our AI features:

  • Operational logs, such as error and infrastructure logs, help us monitor performance and troubleshoot issues. These logs are deleted after 31 days.
  • Conversation and audit data, including your prompts, AI responses, and associated task details, helps us maintain a record of AI activity, investigate issues, and improve our AI features. We do not currently apply a fixed deletion schedule to this data.

Do AI providers retain or train on my data?

No. Our contracts with our AI providers prohibit them from monitoring your data, storing it, or using it for model training. Your data passes through provider infrastructure while a request is being processed, but the provider does not retain it once the request is complete, and our contracts prohibit any secondary use.

Does PortSwigger use my data to improve its AI?

PortSwigger reserves the right to use anonymized data to improve its AI features and diagnose issues.

Processing and AI providers

Where does testing run?

Burp AT in Burp Suite Professional

Burp AT sends requests to the targets you've told it to test, in the same way you would when testing manually. These requests go to your target directly from your local installation of Burp. PortSwigger's AI infrastructure does not connect to your target.

Burp AT captures its traffic in the Logger, so it is fully visible to you. It also attaches the relevant requests and responses to every issue it raises, so you can see exactly what happened and reproduce any findings.

Burp AT in Burp Suite enterprise platform

Burp AT's testing tools run in a PortSwigger-hosted test environment, rather than in your local installation of Burp. Burp AT uses the scope and authentication settings of the site, and any background context that you set for the site.

Burp AT is available for Cloud instances only. You can only test sites configured to use PortSwigger-hosted scanning resources. For more information, see Burp AT in Burp Suite enterprise platform.

How does Burp send and process your data?

When you use an AI feature, Burp sends your data to PortSwigger's AI infrastructure, which manages communication with the AI provider:

  1. Request: Your request data is sent to PortSwigger's AI infrastructure. In Burp Suite Professional, this is sent from your desktop client. In Burp Suite DAST, it is sent from a dedicated scanning resource created specifically to handle the investigation.
  2. Authentication: PortSwigger verifies your license. Only licensed users can access the AI service.
  3. Task processing: A temporary processing agent is created to handle your request. It is decommissioned immediately after the task is complete, and is never reused across requests or users.
  4. Provider transmission: The agent passes your data to the AI provider.
  5. Provider processing: The AI provider processes your data and returns a response to Burp. It does not retain any of your data once processing is complete.
  6. Storage: PortSwigger stores your prompt, the AI response, and related metadata to support troubleshooting, auditing, and billing.

PortSwigger's AI infrastructure runs on AWS in the US-East (Virginia) and EU-West (Ireland) regions.

Which AI models are used, and can I choose?

Not currently. PortSwigger uses a multi-model approach to get the best results across a wide range of security testing tasks, and selects the model for each task based on extensive performance testing, matching each feature to the model that delivers the most accurate and reliable results. We currently use models from OpenAI and Anthropic.

We only use models that meet our strict data privacy standards, and providers that can guarantee your data is not used for training. Our infrastructure manages the connection to these models, so we can upgrade model versions after assessing them. These updates happen automatically, giving you access to current AI versions without the need to update Burp.

Where is data processed?

Burp AT in Burp Suite Professional

In Burp Suite Professional, Burp AT enables you to select whether you want data to be processed in the US or EU. Select the region before sending the project's first message. For more information, see Selecting an AI processing region.

This setting covers AI processing from Burp AT's built-in tools. It does not affect AI calls made by scripts.

PortSwigger stores Burp AT task data in EU-West (Ireland), regardless of whether you select US or EU processing. Selecting US processing does not provide US-only data residency.

Burp AT in Burp Suite enterprise platform

By default, our AI providers process Burp AT requests in the US.

AI-enhanced scanning and AI-recorded login sequences in Burp Suite DAST

For AI-enhanced scanning and AI-recorded login sequences in Burp Suite DAST, our AI providers process requests in US data centers. PortSwigger routes requests between its US and EU infrastructure automatically. You cannot select a geographic location for these features.

What happens if there's an outage?

We operate failover systems to keep the AI features available. If the infrastructure serving a request becomes unavailable, requests are automatically routed to other infrastructure to maintain service.

In Burp Suite Professional, requests from projects configured to use the EU processing region run through AWS Bedrock in Ireland. If the primary service becomes unavailable, then requests fail over to AWS Bedrock in Frankfurt. If no EU processing route is available, then the request fails.

Control over testing

Does testing start automatically?

Burp AT in Burp Suite Professional

No. Burp AT only runs when you give it a prompt or explicitly start a task from another Burp tool. Otherwise it takes no action, and sends no data to PortSwigger or our AI providers. Once running, it works within the autonomy levels you set, and asks for approval on anything you haven't configured it to be able to do on its own.

Burp AT in Burp Suite enterprise platform

A new User guided test starts testing only when you send a prompt in the chat.

An Autonomous test starts automatically, either as soon as possible or on a schedule. You can run it once or set a repeating schedule. You do not need to enter a prompt in the chat to start each scheduled test.

AI-enhanced scanning and AI-recorded login sequences in Burp Suite DAST

AI features are not available by default. An administrator must enable them for your installation before they appear in the UI. Once enabled, they only run against sites you have configured.

AI-enhanced scanning automatically investigates selected issues found during scans. For more information, see Configuring AI-enhanced scanning.

Can Burp AT take actions without my approval?

Burp AT in Burp Suite Professional

Yes, but only if you configure it to. You have full control over what each tool can do without approval. When a tool call needs approval, Burp AT pauses and waits for your decision. For more information, see Configuring autonomy.

Burp AT in Burp Suite enterprise platform

In a User guided test, you respond to approval requests as Burp AT works. Some actions can run without your approval, including scripts supplied with PortSwigger's skills.

Autonomous tests allow most tools to run without approval for each action. Some high-impact tools may still require your approval.

For the setup steps and approval controls, see Running your first agentic test.

Can I control which targets are tested?

Burp AT in Burp Suite Professional

Burp AT works within the scope you set, and checks whether a target is in scope before it acts.

Burp AT can edit scope if you allow it, using its Add to scope and Remove from scope tools. You can restrict or disable these individually in Settings > Tools. For details on what each tool can and can't do, see Configuring autonomy.

This scope check applies to Burp AT's own tool actions. Custom code that it runs through its scripting tools can send requests directly, including to targets outside your defined scope. If you need to prevent this, disable the scripting tools in Settings > Tools.

Burp AT checks tool calls against the permissions you've set before they run. HTTP tools also check your current testing scope. Burp's own tooling enforces these limits, rather than leaving them to AI to interpret. For more information, see Configuring autonomy.

Burp AT in Burp Suite enterprise platform

Yes. Burp AT uses the site's scope, including any exclusions. You configure this in the site's settings. Burp AT cannot change the scope through its tools.

Burp's tools check scope when sending requests or starting to crawl, audit, and fuzz. When fuzzing, Burp AT also checks each request generated from a payload before sending it.

Burp AT can run scripts supplied with PortSwigger's skills. These scripts can make network calls outside Burp's HTTP tools, bypassing scope checks. Burp AT cannot write and run custom scripts in the enterprise platform.

AI-enhanced scanning and AI-recorded login sequences in Burp Suite DAST

Yes. You can use Burp's scope settings to restrict these AI features to specific hosts and URLs. In DAST, you can also control which issue severity and confidence combinations are investigated on a per-site basis.

For more information, see Configuring AI-enhanced scanning.

What traffic controls apply to agentic tests?

Burp AT in Burp Suite enterprise platform

Scanner tasks and requests sent through Burp's bulk request system use resource-pool limits. Direct requests and some requests sent by scripts bypass these limits.

Agentic tests and the scans they launch do not observe scan freeze windows.

Could testing disrupt a production target?

Burp AT in Burp Suite Professional

Burp AT sends the same kinds of requests to your target that you would when testing manually - it has no ability to affect a site beyond what Burp's tools can already do.

Burp AT's HTTP tools are bound by your testing scope. Scripts can make network calls outside these tools and bypass scope checks.

Approval requirements depend on the autonomy mode and tool settings. In Smart mode, bundled skill scripts run without asking for your approval. For tight control on a sensitive target, run the task in Manual mode and set the tools you want to supervise to Ask. For more information, see Configuring autonomy.

Burp AT in Burp Suite enterprise platform

Potentially, depending on the nature of your testing. Burp AT sends live requests to your target. Its tools can crawl, audit, and fuzz the application. These requests may change application data or disrupt the target. To control which areas Burp AT tests and which accounts it uses, configure the site's scope and authentication settings. For more control over the test as it runs, use a User guided test so that you can review and approve actions that need your permission. Scripts supplied with PortSwigger's skills can run without asking for your approval.

Can Burp AT send destructive requests?

Burp AT in Burp Suite Professional

Yes, if you allow it to. Burp AT can send any request you could send manually, including one that changes or deletes data.

Burp AT's HTTP tools are bound by your testing scope. Scripts can make network calls outside these tools and bypass scope checks. Some high-impact tools always require your approval.

To review every request before Burp AT sends it:

  1. Go to Settings > Tools to open Tool settings.
  2. Go to the Manual mode tab and set Send request to Ask.
  3. Select Manual from the Mode drop-down in the message box.

Burp AT then asks for your approval each time it wants to send a request. Per-tool permissions apply only in Manual mode.

When a custom script needs to send a request, it sends it directly. Requests originating from custom scripts don't pass through the Send request tool. Custom scripts always require approval before Burp AT can run them. We strongly recommend that you read a script before approving it. To block Burp AT from running scripts, disable the scripting tools in Settings > Tools.

Burp AT in Burp Suite enterprise platform

Yes. Burp AT's request-sending tool can send requests that change or delete data. Autonomous tests allow tools to run without approval for each action, although some tools can still require your approval.

For more control over testing, use a User guided test, where you can review and approve actions that need your permission. Scripts supplied with PortSwigger's skills can run without asking for your approval.

How do DAST's AI features stay focused on security testing?

These AI features use structured prompts to keep the AI focused on security testing, reducing the risk of hallucinations or unintended actions. There are also built-in limits on the number of steps the AI can take during a task.

In Burp Suite DAST, AI-enhanced scanning has additional guardrails that block destructive HTTP methods (such as DELETE and PUT) and SQL operations that could cause data loss. These run automatically and cannot be disabled by users.

Can I stop testing mid-task?

Burp AT in Burp Suite Professional

Yes. While Burp AT is working, click Stop to stop it immediately.

Burp AT in Burp Suite enterprise platform

Yes. You can stop a test from Agentic tests > Agentic tests. For more information, see Stopping an agentic test. When a test is stopped, its environment shuts down and any work is paused. Requests already in progress may continue after you stop the test.

Reopening a successfully stopped test restarts its environment without resuming AI testing.

The Stop button in the chat ends the current chat turn, but does not stop the test as a whole.

AI-enhanced scanning and AI-recorded login sequences in Burp Suite DAST

To stop AI-enhanced scanning, cancel the scan.

Who can use Burp AT in the enterprise platform?

Users need the Use agentic testing permission on a site to create, stop and delete agentic tests on that site. For details, see Managing access to Burp AT.

Can I disable AI features?

Burp AT in Burp Suite Professional

Yes. To turn off all of Burp's AI features, go to Settings > AI and select Disable AI features. This stops all AI communication, including Burp AT, and grays out AI options throughout Burp.

To limit what Burp AT can do without turning it off completely, consider disabling individual tools. For more information, see Configuring autonomy.

Burp AT in Burp Suite enterprise platform

An administrator can turn Burp AT on or off for the whole instance. The Enable Burp AT setting also controls access to the AI features in Burp Suite DAST. For more information, see Turning Burp AT on or off.

AI-enhanced scanning and AI-recorded login sequences in Burp Suite DAST

Yes. Access is managed at the organization level by an administrator. Go to Settings > Burp AT and toggle Enable Burp AT. You need the Enable/Disable Burp AT for the installation permission to change this setting. When disabled, AI features are removed from the UI and any AI results from previous scans are hidden.

Security and compliance

What security controls protect the AI infrastructure?

Our AI infrastructure uses server- and client-side input validation, and token-based authentication that limits access to licensed users.

All communication between Burp, PortSwigger, and the AI providers is encrypted using TLS 1.2 or later.

How does PortSwigger protect stored data?

PortSwigger encrypts all stored data using AES-256. Role-based permissions limit access to authorized PortSwigger staff who need the data for troubleshooting. PortSwigger logs every internal interaction with your data.

Can data from one project leak into another?

Burp AT in Burp Suite Professional

No. Each task is part of the Burp project you're working in. Burp AT can only see and act on the data in that project, so work from one project can't be seen by another.

Burp AT in Burp Suite enterprise platform

Each agentic test has its own conversation and saved Burp project. Burp AT uses the site's settings and background context for the test. Issues found by an agentic test also appear in the site, folder, and global Issues lists.

What happens if there's a security incident involving an AI provider?

In this case, PortSwigger would respond according to its ISO 27001-aligned incident response process and its contractual obligations with the affected provider. AI usage is logged internally to support our investigations.

Is Burp's AI covered by PortSwigger's compliance and Data Processing Agreement?

Yes. PortSwigger's AI is covered by PortSwigger's ISO 27001 certification, and PortSwigger's Data Processing Agreement covers all personal data processed on your behalf. For full details, see the PortSwigger Trust Center.