Skip to main content

Open to businesses · €50 starting credit

Security workspace: an AI security chatbot you supervise.

The LOKI security workspace is a chat-driven AI security workspace inside the LOKI client portal. You describe in plain language what you want tested. The assistant proposes concrete tool steps, and they run in isolated cloud sandboxes, not on your laptop. Before an active step runs you see the exact tool, target and command and decide whether it goes ahead. Every step lands in an audit log.

Only for websites you add yourself after confirming that you are authorized to test them. LOKI is notified of every site that is added.

You start with €50 credit. Every paid step shows its cost first.

LOKISecurity WorkspaceExample
  1. Scope
  2. Scan
  3. Findings
  4. Fix & retest
  5. Report

Test my site: shop.example.com

Scope noted. Running the first checks.

  • TLS and certificate
  • Security headers
  • Exposed files

3 confirmed findings.

  • HighBackup file readable at /backup.zipFixed
  • MediumSession cookie without Secure flagFixed
  • LowNo Content-Security-Policy headerFixed

Fixed all three. Test again.

Retest done. All three are closed.

Ask anything about your security

How it works

From a sentence in chat to an approved, logged step.

  1. 01

    Describe the test

    Tell the assistant what you want checked, in your own words: for example the login of your customer portal or the headers of your public site.

  2. 02

    Get a concrete proposal

    The assistant turns your request into specific tool steps against the target in your scope. It proposes; it does not decide.

  3. 03

    Review the exact step

    For an active step the workspace shows the tool, the target and the literal command before anything runs. You approve or reject it. The step that runs is checked against the step you reviewed.

  4. 04

    Run in a sandbox, keep the record

    Approved steps run in an isolated cloud sandbox. The request, the decision and the result are written to the audit log of your organisation.

Supervised by design

What keeps a person in charge.

Active steps wait for you
Before an active step runs you see the tool, target and command and approve or reject it. Low-risk passive reads, such as HTTP, TLS and header checks, run straight away and are logged.
Auto-approve is your switch
You can let a conversation run every step its scope allows without asking. It is off until you turn it on, it does not widen the scope, and turning it on or off is itself written to the audit log.
Isolated cloud sandboxes
Tools run in an isolated cloud sandbox tied to your session, not on your own machines. A changed target or command is refused before it runs.
An audit log of every step
Proposed, approved, rejected and executed steps are recorded, with the decision and what came back.
Encrypted per organisation
Conversations, audit logs and the credentials of tools you connect are encrypted per organisation.
Authorized scope only
The workspace is for systems you own or are authorized in writing to test. You confirm that for every site you add, and LOKI is notified of each one.

How it differs

AI security chatbot, scanner or AI security workspace?

General AI chatbotAutomated scannerLOKI security workspace
What it doesAnswers questions and suggests commandsRuns a fixed set of known checksProposes concrete tool steps for your request and runs the approved ones
Where tools runOn your own machine, if you run the commands yourselfOn the scanner's systems or yoursIn an isolated cloud sandbox
Who decides what runsYou, by copying a commandA schedule or whoever starts the scanYou, per active step, with the exact tool, target and command in front of you
What is recordedThe chat historyA scan reportAn audit log of every step and decision
ScopeWhatever is typedThe targets that are configuredOnly the sites you added after confirming you are authorized

The first two columns describe how these kinds of tools typically work; individual products differ.

What it is not

Clear limits.

  • Not a human-reviewed pentest report. Tool output in the workspace is working material; findings checked by a person, with evidence, the fix and a retest, come from a SKYEN pentest.
  • Not a certificate or a compliance statement.
  • Not for consumers. Accounts are for businesses and organisations testing systems they are authorized to test.
  • Not for systems you do not own or are not authorized to test.

Related

Where the workspace fits.

Questions about the security workspace

What is a security workspace?

A security workspace is one place where security testing is requested, run and recorded. The LOKI security workspace is chat-driven: you describe what you want tested, the assistant proposes concrete tool steps, approved steps run in isolated cloud sandboxes and every step is audit-logged. It sits inside the LOKI client portal.

What is an AI security chatbot?

An AI security chatbot is an assistant you talk to about security work. Many only answer questions or write commands for you to run yourself. The assistant in the LOKI security workspace can also run tools, under supervision: before an active step runs you see the exact tool, target and command and approve or reject it.

Can the assistant run anything without my approval?

Low-risk passive reads, such as HTTP, TLS and header checks, run straight away and are logged. Active steps wait for your decision. You can switch a conversation to auto-approve, so that every step its scope allows runs without asking; that is off until you turn it on, and the switch itself is logged.

Where do the tools run?

In isolated cloud sandboxes, not on your own computer. The step that runs is checked against the step that was reviewed: a changed target or command is refused.

How is my data protected?

Conversations, audit logs and the credentials of tools you connect are encrypted per organisation. Access goes through your LOKI client portal sign-in and your organisation membership.

Which systems can I test with it?

Only systems you own or are authorized in writing to test. Before a site enters your scope you tick "I'm authorized to test this target"; that statement is kept with the scope, and LOKI is notified of every site that is added. The workspace is not a tool for testing third parties.

How do I get access and what does it cost?

Create an account with Google. Every new workspace starts with €50 credit, and each paid step shows its cost first. Accounts are for businesses and organisations.

Does the security workspace replace a pentest?

No. A SKYEN pentest ends in a report in which a person has checked every finding, with evidence, the fix and one retest. The workspace is for supervised checks you start yourself, and its tool output is working material. Neither is a certificate.

Start with your own site.

Add a site you are authorized to test, tell the agent what you want checked and follow every step in the chat.

You start with €50 credit. Every paid step shows its cost first.