DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to gate a Bot's browser actions with deny rules with Open Bot

Add a deny rule in the boundaries admin page, retry a browser action, then read the audit log.

Credentials. Logins saved through /settings/passwords let a Bot sign in to websites, so review which accounts are stored before testing.

Who it is forA security-minded operator who needs to show that an AI coworker can be stopped from doing a specific browser action before letting it near company systems.

The problemAn agent that can drive a browser can take actions nobody reviewed, and it is hard to show that a rule blocked one.

The outcomeA tested deny rule in /admin/boundaries, a retried action that is blocked, and an audit entry in /admin/audit that records what happened.

What you need first

  • Docker, for PostgreSQL and the shipped Bots
  • Bun 1.3 or later
  • A CopilotKit account to run `npx --yes copilotkit@latest login`, or a self-hosted Intelligence deployment
  • An OpenAI API key for the proof-of-concept Bot

Steps

  1. Start the stack with bash scripts/start.sh after completing the Quick start.
  2. Open /bot and ask the Bot to open news.ycombinator.com and tell you the top story, so you have a baseline run.
  3. Open /admin/boundaries, add a deny rule or preset that covers the browser action, and save it.
  4. Return to /bot and retry the same request.
  5. Open /admin/audit and check the entries for both attempts.

Prompt for your agent

In the OpenBot repository at <repo-path>, start the stack per README.md, add a deny rule at /admin/boundaries that blocks browser navigation, then retry the news.ycombinator.com request from /bot. Report whether the action was blocked and quote the matching entry from /admin/audit.

Caveat. The README describes the deny rule flow and the audit route but does not show their exact output, so check the result in the UI rather than assuming a rule works as written.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page