← Back to Skills Marketplace
Virtual Desktop Pro v4 -- Universal Browser Execution
by
Wesley Armando
· GitHub ↗
· v4.0.1
· MIT-0
274
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install virtual-desktop-pro
Description
Persistent authenticated browser for OpenClaw via kasmweb/chrome Docker sidecar. Principal logs in once via noVNC — sessions saved permanently in Docker volu...
Usage Guidance
This skill appears to do what it claims, but it grants the agent broad access to any sites you log into via the persistent browser and uses optional third‑party services that can receive data (screenshots, pages) and incur costs. Before installing: 1) Back up your docker-compose.yml; review the one‑liner change before applying. 2) Run the browser sidecar on an isolated VPS or test environment first. 3) Restrict access to port 6901 (prefer SSH tunnel or firewall rule to your IP). 4) Use a strong VNC_PW and rotate it if you stop using the skill. 5) Only set CAPSOLVER/BROWSERBASE/ANTHROPIC/TELEGRAM keys if you trust those services; expect CAPTCHA screenshots and page content to be transmitted. 6) Inspect the kasmweb/chrome image version and consider pinning/updating it from an official source. 7) Monitor /workspace/logs and audit the AUDIT.md and screenshots for unexpected activity. If you want higher assurance, ask the publisher for provenance of the repo and a signed release or run the container with network egress rules to limit external destinations.
Capability Analysis
Type: OpenClaw Skill
Name: virtual-desktop-pro
Version: 4.0.1
The skill bundle performs high-privilege system modifications, including editing the host's `docker-compose.yml` and `openclaw.json` files, and using `docker exec` to install Playwright dependencies. These actions in `SKILL.md` facilitate a persistent authenticated browser environment that stores user sessions and opens port 6901 for noVNC access, creating a significant attack surface. While the logic in `browser_control.py` for CAPTCHA solving (via `capsolver.com`) and stealth proxying (via `browserbase.com`) aligns with the stated purpose of browser automation, the level of host-level control and session persistence is inherently risky.
Capability Assessment
Purpose & Capability
Name/description (persistent Chrome sidecar + authenticated sessions) align with required binaries (docker, python3), required env vars (VNC_PW, BROWSER_CDP_URL) and the included browser_control.py. External services listed (CapSolver, Browserbase, Anthropic) are optional and match features (CAPTCHA solving, residential proxy, Claude Vision).
Instruction Scope
SKILL.md instructs the agent to edit docker-compose.yml, create a persistent Docker volume, open port 6901 (or use SSH tunnel), and write logs/screenshots and learning files into /workspace. It also uses Telegram notifications for CAPTCHA/manual actions. These are all within the scope of running a persistent browser, but they do grant broad access to any sites you log into and may send screenshots/notifications externally (Telegram). The skill also reads some workspace files for context (/workspace/TOOLS.md, .learnings/*) — this is reasonable but worth noting if those files contain sensitive data.
Install Mechanism
There is no formal install spec, so installation is instruction-driven (pull kasmweb/chrome via Docker, install Playwright/requests in the container). Pulling a ~2GB Docker image is expected. The repo doesn't contain opaque external download URLs; the main runtime download is the official kasmweb/chrome image and Python packages. Confirm you are comfortable pulling that image and the network access required to fetch Playwright runtimes.
Credentials
Required env vars (VNC_PW, BROWSER_CDP_URL) are proportional to a noVNC/CDP browser sidecar. Optional keys (CAPSOLVER_API_KEY, BROWSERBASE_API_KEY, ANTHROPIC_API_KEY, TELEGRAM_BOT_TOKEN) are justified by their named features. Caveats: providing these keys gives the skill ability to send data to third-party services (CAPSolver, Browserbase, Anthropic) and will incur costs; Telegram notifications may include screenshots or session status and could leak sensitive content if the Telegram channel is not private.
Persistence & Privilege
The skill requests persistent sessions (Docker volume 'browser-profile') and writes logs/screenshots into /workspace, which is consistent with its purpose. always:false and no modification of other skills' configs are used. Autonomous invocation is allowed by default but not uncommon; combine with the above (persistent sessions + optional external keys) only if you trust the runtime and keys.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install virtual-desktop-pro - After installation, invoke the skill by name or use
/virtual-desktop-pro - Provide required inputs per the skill's parameter spec and get structured output
Version History
v4.0.1
Version 4.0.1
- No changes detected from the previous version (4.0.0).
- This release is functionally identical; no files were modified.
v4.0.0
**Major update: Virtual Desktop now provides a persistent, authenticated browser for OpenClaw agents via Docker with advanced automation and analysis capabilities.**
- Adds persistent browser session using kasmweb/chrome Docker sidecar — principal logs in once, sessions are saved.
- Fully automates clicks, form fills, navigation, uploads, downloads, screenshots, and CAPTCHA solving.
- Sessions persist across restarts for seamless workflow continuity.
- Integrates Claude Vision for advanced document and page analysis.
- Captures structured data, error states, and navigation learnings in dedicated workspace files for traceability and improvement.
- Improved setup and environment requirements for robust, secure operation.
Metadata
Frequently Asked Questions
What is Virtual Desktop Pro v4 -- Universal Browser Execution?
Persistent authenticated browser for OpenClaw via kasmweb/chrome Docker sidecar. Principal logs in once via noVNC — sessions saved permanently in Docker volu... It is an AI Agent Skill for Claude Code / OpenClaw, with 274 downloads so far.
How do I install Virtual Desktop Pro v4 -- Universal Browser Execution?
Run "/install virtual-desktop-pro" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Virtual Desktop Pro v4 -- Universal Browser Execution free?
Yes, Virtual Desktop Pro v4 -- Universal Browser Execution is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Virtual Desktop Pro v4 -- Universal Browser Execution support?
Virtual Desktop Pro v4 -- Universal Browser Execution is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Virtual Desktop Pro v4 -- Universal Browser Execution?
It is built and maintained by Wesley Armando (@georges91560); the current version is v4.0.1.
More Skills