Browserbase Persist with captcha

Create and manage persistent Browserbase cloud browser sessions with authentication persistence. Use when the user needs to automate browsers, maintain logged-in sessions across interactions, scrape authenticated pages, or manage cloud browser instances. Handles session creation, context-based auth persistence, keep-alive reconnection, captcha solving, session recording, screenshots, and session cleanup.

Security Scan

The skill is generally coherent with its stated purpose (managing Browserbase sessions) but has a few mismatches and privacy-sensitive defaults (session recording and automatic CAPTCHA solving), plus minor inconsistencies that warrant caution before installing.

Purpose & Capability

Name, README, SKILL.md, and the included CLI script all consistently implement Browserbase session creation, context persistence, navigation, screenshots, recordings, and captcha solving. The required env vars (BROWSERBASE_API_KEY, BROWSERBASE_PROJECT_ID) are appropriate for a cloud browser API client.

Instruction Scope

The runtime instructions and the script enable recording every session by default and enable automatic CAPTCHA solving by default. These features can capture sensitive user credentials, page contents, and interactions. The script also constructs/uses a WebSocket connect URL that may include the API key as a query parameter (exposes credential in a URL), and the setup command performs a full smoke test that creates a live session and navigates to a site — these are consistent with the purpose but are high-impact actions that should be explicitly authorized by the user. The SKILL.md does not clearly warn about privacy implications of default recording/solver behavior.

Install Mechanism

There is no platform install spec (instruction-only + included Python script). Dependencies are installed via pip and Playwright per the docs (requirements.txt present). This is a common, moderate-risk approach: it requires the user to run pip and playwright install commands (no opaque remote downloads), but the user must trust the pip packages and run Playwright (which downloads browsers).

Credentials

Only two credentials are required (API key and project ID), which is proportionate to the stated capability. However: (1) the code also respects BROWSERBASE_CONFIG_DIR (not declared in requires.env), which lets the skill read/write a path under the user's home; (2) the script may include the API key in a constructed WebSocket URL if session.connect_url is missing, exposing the key in process args/URLs; and (3) the skill persists named contexts to disk (~/.browserbase/contexts.json) by default, storing context IDs that map to authentication state. These are reasonable for functionality but are sensitive and should be highlighted to users.

Persistence & Privilege

The skill does not request always:true and does not modify other skills. It writes its own config file (~/.browserbase/contexts.json by default) and may create session recordings on the remote service (and allows downloading them). That is expected for session-management tooling but is a permanence/privacy consideration (local context file plus remote recordings).

What to consider before installing

This skill appears to implement exactly what it says, but it has privacy- and credential-related implications you should consider before installing: - Default behavior records every session and automatically solves CAPTCHAs. Recordings and solved login flows can capture sensitive credentials and page content. If you will log into accounts, disable recording and captcha solving (use the provided flags) or avoid using the skill for sensitive sites. - The script persists named context mappings to ~/.browserbase/contexts.json (or to a directory you set via BROWSERBASE_CONFIG_DIR). If that file or your machine is shared, contexts may reveal which accounts you used. Consider setting BROWSERBASE_CONFIG_DIR to a controlled directory with appropriate permissions. - The code may construct a connect WebSocket URL that includes your API key as a query parameter if the SDK doesn't supply one. Treat your BROWSERBASE_API_KEY as sensitive: store it in a secure place and rotate it if you suspect exposure. - Installation relies on pip and Playwright; installing Playwright downloads browser binaries. Only proceed if you trust the browserbase package and its dependencies. Review scripts/browserbase_manager.py before running, and run setup in an isolated environment (or container) first. - Minor inconsistencies: SKILL.md/metadata don’t declare the optional BROWSERBASE_CONFIG_DIR env var and the registry lists no homepage/source; the required binary list mentions "uv" which is uncommon — verify what that refers to in your environment. If you trust the Browserbase service and accept recorded sessions/captcha solving, the skill is functionally coherent. If you need stronger privacy or auditability, ask for changes (clear opt-in for recording/solver, explicit warnings, configurable local config path) or run the tool in an isolated environment and review all code before use.

Browserbase Sessions Skill

Manage persistent cloud browser sessions via Browserbase. This skill creates browser sessions that preserve authentication (cookies, local storage) across interactions, automatically solve CAPTCHAs, and record sessions for later review.

First-Time Setup

Step 1 — Get your Browserbase credentials

1. Sign up at browserbase.com if you haven't already.
2. Go to Settings → API Keys and copy your API key (starts with bb_live_).
3. Go to Settings → Project and copy your Project ID (a UUID).

Step 2 — Install dependencies

cd {baseDir}/scripts && pip install -r requirements.txt
playwright install chromium

Or with uv:

cd {baseDir}/scripts && uv pip install -r requirements.txt
uv run playwright install chromium

Step 3 — Set environment variables

export BROWSERBASE_API_KEY="bb_live_your_key_here"
export BROWSERBASE_PROJECT_ID="your-project-uuid-here"

Or configure via OpenClaw's skills.entries.browserbase-sessions.env in ~/.openclaw/openclaw.json.

Step 4 — Run the setup test

This validates everything end-to-end (credentials, SDK, Playwright, API connection, and a live smoke test):

python3 {baseDir}/scripts/browserbase_manager.py setup

You should see "status": "success" with all steps passing. If any step fails, the error message tells you exactly what to fix.

Defaults

Every session is created with these defaults to support research workflows:

• Captcha solving: ON — Browserbase automatically solves CAPTCHAs so login flows and protected pages work without manual intervention. Disable with --no-solve-captchas.
• Session recording: ON — Every session is recorded as a video you can download later for review or sharing. Disable with --no-record.
• Auth persistence — Use contexts with --persist to stay logged in across sessions.

Available Commands

All commands are run via the manager script:

python3 {baseDir}/scripts/browserbase_manager.py <command> [options]

Setup & Validation

Run the full setup test:

python3 {baseDir}/scripts/browserbase_manager.py setup

Context Management (for authentication persistence)

Create a named context to store login state:

python3 {baseDir}/scripts/browserbase_manager.py create-context --name github

List all saved contexts:

python3 {baseDir}/scripts/browserbase_manager.py list-contexts

Delete a context (by name or ID):

python3 {baseDir}/scripts/browserbase_manager.py delete-context --context-id github

Session Lifecycle

Create a new session (captcha solving and recording enabled by default):

# Basic session
python3 {baseDir}/scripts/browserbase_manager.py create-session

# Session with saved context (persist=true saves cookies on close)
python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id github --persist

# Keep-alive session for long research (survives disconnections)
python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id github --persist --keep-alive --timeout 3600

# Full options
python3 {baseDir}/scripts/browserbase_manager.py create-session \
  --context-id github \
  --persist \
  --keep-alive \
  --timeout 3600 \
  --region us-west-2 \
  --proxy \
  --block-ads \
  --viewport-width 1280 \
  --viewport-height 720

List all sessions:

python3 {baseDir}/scripts/browserbase_manager.py list-sessions
python3 {baseDir}/scripts/browserbase_manager.py list-sessions --status RUNNING

Get session details:

python3 {baseDir}/scripts/browserbase_manager.py get-session --session-id <id>

Terminate a session:

python3 {baseDir}/scripts/browserbase_manager.py terminate-session --session-id <id>

Browser Automation

Navigate to a URL:

# Navigate and get page title
python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id <id> --url "https://example.com"

# Navigate and extract text
python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id <id> --url "https://example.com" --extract-text

# Navigate and save screenshot
python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id <id> --url "https://example.com" --screenshot /tmp/page.png

# Navigate and take full-page screenshot
python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id <id> --url "https://example.com" --screenshot /tmp/full.png --full-page

Take a screenshot of the current page (without navigating):

python3 {baseDir}/scripts/browserbase_manager.py screenshot --session-id <id> --output /tmp/current.png
python3 {baseDir}/scripts/browserbase_manager.py screenshot --session-id <id> --output /tmp/full.png --full-page

Execute JavaScript:

python3 {baseDir}/scripts/browserbase_manager.py execute-js --session-id <id> --code "document.title"

Get cookies:

python3 {baseDir}/scripts/browserbase_manager.py get-cookies --session-id <id>

Recordings, Logs & Debug

Download a session recording video (session must be terminated first):

python3 {baseDir}/scripts/browserbase_manager.py get-recording --session-id <id> --output /tmp/session.webm

Get session logs:

python3 {baseDir}/scripts/browserbase_manager.py get-logs --session-id <id>

Get the live debug URL (for visual inspection of a running session):

python3 {baseDir}/scripts/browserbase_manager.py live-url --session-id <id>

Common Workflows

Workflow 1: Multi-session research with persistent login

# 1. One-time: create a named context for the site
python3 {baseDir}/scripts/browserbase_manager.py create-context --name myapp

# 2. Start a research session (captchas auto-solved, recording on)
python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id myapp --persist --keep-alive --timeout 3600

# 3. Navigate to login — captchas solved automatically
python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id <id> --url "https://myapp.com/login"
# Use execute-js to fill forms and submit

# 4. Do research, take screenshots
python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id <id> --url "https://myapp.com/dashboard" --extract-text
python3 {baseDir}/scripts/browserbase_manager.py screenshot --session-id <id> --output /tmp/dashboard.png

# 5. Terminate (cookies saved to context)
python3 {baseDir}/scripts/browserbase_manager.py terminate-session --session-id <id>

# 6. Download recording to share
python3 {baseDir}/scripts/browserbase_manager.py get-recording --session-id <id> --output /tmp/research.webm

# 7. Next day: new session, already logged in!
python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id myapp --persist --keep-alive --timeout 3600

Workflow 2: Screenshot documentation

python3 {baseDir}/scripts/browserbase_manager.py create-session
python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id <id> --url "https://docs.example.com" --screenshot /tmp/docs_home.png
python3 {baseDir}/scripts/browserbase_manager.py navigate --session-id <id> --url "https://docs.example.com/api" --screenshot /tmp/docs_api.png --full-page
python3 {baseDir}/scripts/browserbase_manager.py terminate-session --session-id <id>

Workflow 3: Record and share a walkthrough

# Session recording is ON by default
python3 {baseDir}/scripts/browserbase_manager.py create-session --context-id myapp --persist
# ... do your walkthrough (navigate, click, etc.) ...
python3 {baseDir}/scripts/browserbase_manager.py terminate-session --session-id <id>
# Download the video
python3 {baseDir}/scripts/browserbase_manager.py get-recording --session-id <id> --output /tmp/walkthrough.webm

Important Notes

• Captcha solving is ON by default. Browserbase handles CAPTCHAs automatically during login flows and page loads. Use --no-solve-captchas to disable.
• Recording is ON by default. Every session is recorded. Download with get-recording after termination. Use --no-record to disable.
• Connection timeout: 5 minutes to connect after creation before auto-termination.
• Keep-alive sessions survive disconnections and must be explicitly terminated.
• Context persistence: Wait a few seconds after terminate-session --persist before creating a new session with the same context.
• Named contexts: Use --name with create-context to save friendly names (e.g. github, slack). Use the name anywhere a context ID is expected.
• One context per site: Use separate contexts for different authenticated sites.
• Avoid concurrent sessions on the same context.
• Regions: us-west-2 (default), us-east-1, eu-central-1, ap-southeast-1.
• Session timeout: 60–21600 seconds (max 6 hours).

Error Handling

All commands return JSON output. On error, the output includes an "error" key. Common errors:

• APIConnectionError: Browserbase API unreachable
• RateLimitError: Too many concurrent sessions for your plan
• APIStatusError: Invalid parameters or authentication failure
• Missing env vars: Set BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID

Reference

For full API details, read {baseDir}/references/api-quick-ref.md.