Vellum Browser Use

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

assistant/CLAUDE.md

assistant/src/approvals/CLAUDE.md

assistant/src/notifications/CLAUDE.md

assistant/src/runtime/CLAUDE.md

gateway/CLAUDE.md

Audit 0.4.1 · source sha 19bc86343b63 · 14 Oct 2026Report an issue or request a re-scan

• Publishervellum-ai GitHub organizationOwner of the repository this skill is read from
• Source foldervellum-ai/vellum-assistant/skills/vellum-browser-useThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdict19bc86343b63A new audit runs when the source changes
• Repository statusNot archivedLast push 1 day ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Browse the web using `assistant browser` CLI commands

---
name: vellum-browser-use
description: Browse the web using `assistant browser` CLI commands
compatibility: "Designed for Vellum personal assistants"
metadata:
  emoji: "🌐"
  vellum:
    category: "browsing"
    display-name: "Browser"
    activation-hints:
      - "Load first if you need to browse the web (navigating, clicking, extracting web content) via `assistant browser` commands"
---

Use this skill to browse the web. All browser operations are executed through the `assistant browser` CLI, invoked via `bash` or `host_bash`. Each operation is a subcommand:

| Command                               | Description                                        |
| ------------------------------------- | -------------------------------------------------- |
| `assistant browser navigate`          | Navigate to a URL                                  |
| `assistant browser snapshot`          | List interactive elements on the current page      |
| `assistant browser screenshot`        | Take a visual screenshot                           |
| `assistant browser click`             | Click an element                                   |
| `assistant browser type`              | Type text into an input                            |
| `assistant browser press-key`         | Press a keyboard key                               |
| `assistant browser scroll`            | Scroll the page or a specific element              |
| `assistant browser select-option`     | Select an option from a native `<select>` element  |
| `assistant browser hover`             | Hover over an element to reveal menus/tooltips     |
| `assistant browser wait-for`          | Wait for a condition                               |
| `assistant browser extract`           | Extract page text content                          |
| `assistant browser wait-for-download` | Wait for a file download to complete               |
| `assistant browser fill-credential`   | Fill a stored credential into a form field         |
| `assistant browser attach`            | Attach the Chrome debugger to the active tab       |
| `assistant browser detach`            | Detach the Chrome debugger from the active tab     |
| `assistant browser close`             | Close the browser page                             |
| `assistant browser status`            | Diagnose browser backend readiness and setup steps |

## Getting Started — Check Browser Readiness

Before using any browser commands, run `assistant browser --json status` first to check which browser backends are available. The status command returns JSON with readiness information for each backend mode:

```bash
assistant browser --json status
```

The response includes:

- `recommendedMode` — the best available backend (use this)
- `modes[]` — per-mode status with `available`, `summary`, and `userActions` (remediation steps)

For `--virtual-desktop`, Chrome and desktop components are included in the assistant image. Browser and computer use start the existing desktop without installing dependencies. If components are missing, report the image problem; do not install packages or launch a separate Chrome process.

## Browser Modes

Use `--browser-mode <mode>` on the `assistant browser` parent command to pin the browser backend:

| Value         | Backend          | Description                                                           |
| ------------- | ---------------- | --------------------------------------------------------------------- |
| `auto`        | Automatic        | Default. Picks the best available backend based on context.           |
| `extension`   | Chrome extension | Routes through the user's Chrome browser via the extension debugger.  |
| `cdp-inspect` | CDP inspect      | Connects to an already-running Chrome instance via DevTools Protocol. |
| `local`       | Playwright       | Drives a dedicated Playwright-managed Chromium instance.              |

```bash
assistant browser --browser-mode extension navigate --url http://www.example.com
```

### Prefer the Chrome Extension

The **Chrome extension** (`extension` mode) is the preferred browser backend. It is:

- More secure than Chrome's native remote debugging
- Uses the user's real browser profile (cookies, sessions, saved logins)
- Best experience for interacting with the user's actual browsing context

If the status check shows the extension is **not available**, encourage the user to install and pair it:

1. Install the **Vellum Assistant Chrome Extension** from the Chrome Web Store: https://chromewebstore.google.com/detail/vellum-assistant-browser/hphbdmpffeigpcdjkckleobjmhhokpne
2. Open the extension in Chrome and pair it with the assistant.

The status response's `userActions` array for the `extension` mode provides these same steps when the extension is not connected.

## When a Page Cannot Be Reached

If navigate, curl, or any fetch times out, hits an auth wall, or cannot reach a host (VPN, company login, internal dashboard):

1. Tell the user a connected desktop app or Chrome extension can open the page in a browser where they are already logged in.
2. Give the install links:
   - Desktop app: https://www.vellum.ai/downloads
   - Chrome extension: https://chromewebstore.google.com/detail/vellum-assistant-browser/hphbdmpffeigpcdjkckleobjmhhokpne
3. Offer those first. Only ask for a screenshot or pasted page content if they cannot install either.
4. On iOS or Android there is no in-app browser and no extension to install on the phone. Offer the desktop app or Chrome extension on a computer. Do not describe a browser panel.

### Fallback Modes

If the user declines to install the extension:

- **`cdp-inspect`** — Connects to an already-running Chrome instance via DevTools Protocol (Chrome 146+). Requires enabling remote debugging in Chrome settings.
- **`local`** — Drives a dedicated Playwright-managed Chromium instance. Last resort — does not use the user's browser profile.

Only fall back to these if the user explicitly indicat

Excerpt, first 6,001 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/vellum-ai/vellum-assistant
git -C vellum-assistant checkout 19bc86343b63

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 19bc86343b63

Questions about Vellum Browser Use

• github.com/vellum-ai/vellum-assistant/tree/main/skills/vellum-br — the audited source at commit 19bc86343b63 and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology