Skip to content
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Access Restrictions and Exceptions

Restrict which hosts, paths, and accounts can interact with your agents, and define phrases a policy should treat as safe.

This page covers part of the Create Guardrail Policies form.

Access Restrictions

Configure controls to restrict which hosts, paths, and account types can interact with your agents.

Block host / path

Block outbound traffic by host or path pattern to prevent agents from reaching unauthorised external services or endpoints.

1

Enter a pattern

Enter a host or path pattern in the Host or path pattern field.

2

Add it to the list

Select Add to include the pattern in the blocked list.

The Blocked patterns list displays all configured entries. You can review and remove patterns from this list at any time.

Akto sits between your agents and their outbound traffic. When a request is made, Akto checks the destination host or path against the blocked patterns and denies any match before it reaches the target.

Block personal accounts

Prevent users with personal or consumer email accounts from accessing the AI agent. Enterprise accounts using company email domains are allowed through.

  • Enable personal account blocking to restrict access to organisation-managed accounts only.

Block public sharing

Block chats and artifacts from being shared through public links, so conversations and generated content stay inside your organisation.

  • Enable public sharing blocking to stop users from creating public links to chats and artifacts in supported AI tools.

Personal account blocking is enforced through the browser extension, and currently supports the following browser LLMs: chatgpt.com, gemini.google.com, claude.ai, copilot.microsoft.com, and grok.com. Requires Akto browser extension v1.0.69 or later; it is currently supported only through the browser extension, with AI Endpoint Shield Agent support coming soon.

Exceptions

Configure phrases that this policy's own detectors should treat as safe and skip, without affecting how other guardrail policies evaluate the same traffic.

Ignore Phrases

1

Enter a phrase

Enter a phrase in the Ignore phrases field (e.g. your product name or sample test data). Phrases are matched as a whole word by default.

2

Set matching options (optional)

Enable Regex to match the entry as a regular expression instead of literal text. Enable Case sensitive to match the phrase's casing exactly.

3

Add the phrase

Select Add phrase to include it in the ignored list.

The Ignored phrases list displays a count of configured entries and lets you remove any phrase at any time.

Ignore phrases only affect this policy's own detectors, so other guardrail policies evaluated on the same traffic still see the real text.

Last updated