$ ~/registry/skill/composiohq-composio-skills-hyperbrowser-automation

SKILL

hyperbrowser-automation

Name: hyperbrowser-automation
Author: Composio

Automate Hyperbrowser workflows via Rube MCP using current tool schemas first.

Stars

★ 67,763

Source

GitHub

Updated

2026-07-15

// securityCaution

Prompt only, no code
Open source
Community-trusted· 64.7k

Summary

This skill itself is an open-source prompt-style instruction set with no declared local secrets, file access, or local code execution. However, it is designed to connect users to remote Rube MCP/Composio/Hyperbrowser services and trigger external tool actions, so the overall posture is low-to-moderate caution, with most exposure coming from the external service chain rather than the skill text itself.

CredentialsCaution

The material states 'No API keys needed,' but it still requires establishing an ACTIVE Hyperbrowser connection via `RUBE_MANAGE_CONNECTIONS` and following an authentication link. This implies possible third-party account authorization or OAuth-style credentials, even if no environment variable is exposed in the skill itself. No explicit credential theft behavior is described.

Network egressCaution

The README explicitly requires adding the remote MCP endpoint `https://rube.app/mcp` and using Composio/Hyperbrowser-related services for tool discovery, connection management, and execution. Task content, session IDs, and tool arguments are therefore likely sent to these declared external services. The endpoint appears related to the stated functionality, with no unrelated or covert exfiltration target described.

Code executionLow risk

Based on the objective checks, this is a prompt-only skill. The material does not declare any need to install executables locally, spawn local processes, or invoke system commands directly; it mainly describes how to use remote MCP tools. No local code execution privilege request is evident.

Data accessCaution

The skill text itself does not declare local file or system resource access, but once it uses `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`, the effective data access scope depends on permissions granted through the Hyperbrowser/Composio connection. The material does not define a least-privilege boundary, so the external tool-side data access surface warrants caution.

Supply chainLow risk

The source is a GitHub open-source repository with very high community adoption (64.7k stars), which is a strong risk-reducing factor. The visible skill content is primarily documentation/prompt material and does not include executable install scripts. Limitations remain: the license is unspecified, maintenance status is unknown, and the effective Rube/Composio/Hyperbrowser service chain is not fully auditable from this repository alone.

Recommendations

Before connecting, verify the privacy policies, data handling scope, and account authorization permissions of `rube.app/mcp`, Composio, and Hyperbrowser.
When authorizing the Hyperbrowser connection, use a least-privilege account and avoid granting access unrelated to the automation task.
Review the actual tool schemas and parameters returned by `RUBE_SEARCH_TOOLS` before execution to avoid sending unnecessary sensitive content to external services.
Prefer testing this skill in an isolated environment or controlled workspace, and log external connections and tool invocations.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "hyperbrowser-automation" skill from askskill:
1. Download https://raw.githubusercontent.com/ComposioHQ/awesome-claude-skills/master/composio-skills/hyperbrowser-automation/SKILL.md
2. Save it as ~/.claude/skills/hyperbrowser-automation/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// docs

Hyperbrowser Automation via Rube MCP

Automate Hyperbrowser operations through Composio's Hyperbrowser toolkit via Rube MCP.

Toolkit docs: composio.dev/toolkits/hyperbrowser

Prerequisites

Rube MCP must be connected (RUBE_SEARCH_TOOLS available)
Active Hyperbrowser connection via RUBE_MANAGE_CONNECTIONS with toolkit hyperbrowser
Always call RUBE_SEARCH_TOOLS first to get current tool schemas

Setup

Get Rube MCP: Add https://rube.app/mcp as an MCP server in your client configuration. No API keys needed — just add the endpoint and it works.

Verify Rube MCP is available by confirming RUBE_SEARCH_TOOLS responds
Call RUBE_MANAGE_CONNECTIONS with toolkit hyperbrowser
If connection is not ACTIVE, follow the returned auth link to complete setup
Confirm connection status shows ACTIVE before running any workflows

Tool Discovery

Always discover available tools before executing workflows:

RUBE_SEARCH_TOOLS
queries: [{use_case: "Hyperbrowser operations", known_fields: ""}]
session: {generate_id: true}

This returns available tool slugs, input schemas, recommended execution plans, and known pitfalls.

Core Workflow Pattern

Step 1: Discover Available Tools

RUBE_SEARCH_TOOLS
queries: [{use_case: "your specific Hyperbrowser task"}]
session: {id: "existing_session_id"}

Step 2: Check Connection

RUBE_MANAGE_CONNECTIONS
toolkits: ["hyperbrowser"]
session_id: "your_session_id"

Step 3: Execute Tools

RUBE_MULTI_EXECUTE_TOOL
tools: [{
  tool_slug: "TOOL_SLUG_FROM_SEARCH",
  arguments: {/* schema-compliant args from search results */}
}]
memory: {}
session_id: "your_session_id"

Known Pitfalls

Always search first: Tool schemas change. Never hardcode tool slugs or arguments without calling RUBE_SEARCH_TOOLS
Check connection: Verify RUBE_MANAGE_CONNECTIONS shows ACTIVE status before executing tools
Schema compliance: Use exact field names and types from the search results
Memory parameter: Always include memory in RUBE_MULTI_EXECUTE_TOOL calls, even if empty ({})
Session reuse: Reuse session IDs within a workflow. Generate new ones for new workflows
Pagination: Check responses for pagination tokens and continue fetching until complete

Quick Reference

Operation	Approach
Find tools	`RUBE_SEARCH_TOOLS` with Hyperbrowser-specific use case
Connect	`RUBE_MANAGE_CONNECTIONS` with toolkit `hyperbrowser`
Execute	`RUBE_MULTI_EXECUTE_TOOL` with discovered tool slugs
Bulk ops	`RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`
Full schema	`RUBE_GET_TOOL_SCHEMAS` for tools with `schemaRef`

Powered by Composio

Automate BrowseAI workflows to extract web data and monitor page changes.

ComposioGet→

$ loading_