Agent Browser

WarnAudited by ClawScan on May 10, 2026.

Overview

This is a powerful browser-automation skill that is mostly disclosed, but it can reuse logged-in browser sessions and encourages proxy rotation for scraping, so it needs careful review before use.

Install only if you need powerful browser automation and are comfortable supervising it. Use a dedicated profile or test account, avoid importing your normal logged-in browser, encrypt/delete auth state files, verify the external CLI package source, and do not use the proxy-rotation scraping patterns to bypass site limits or bans.

Findings (6)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

An agent using this workflow could act as you on websites where your browser is logged in, and the saved state file could expose account sessions if mishandled.

Why it was flagged

The skill explicitly supports importing authentication from the user's running Chrome session and saving session cookies/localStorage to a local file, which can grant access to logged-in accounts.

Skill content
agent-browser --auto-connect state save ./my-auth.json ... save its cookies + localStorage ... State files contain session tokens in plaintext.
Recommendation

Use a dedicated browser profile or test account when possible, avoid importing your main browser session, encrypt or delete state files, and approve any authenticated action explicitly.

What this means

Using these patterns could violate website rules, trigger account blocking, or cause the agent to perform abusive scraping behavior.

Why it was flagged

The proxy documentation does not just describe corporate or testing proxy use; it explicitly encourages rotating proxies to avoid rate limits and bans while scraping.

Skill content
Proxy configuration for geo-testing, rate limiting avoidance... Rotating Proxies for Scraping ... Rotate through proxy list to avoid rate limiting ... avoid bans
Recommendation

Use proxies only for legitimate testing or approved network routing, respect robots.txt/site terms and rate limits, and avoid automated scraping meant to bypass restrictions.

What this means

JavaScript execution can read or change page content in the active browser context, including authenticated pages.

Why it was flagged

The CLI can execute arbitrary JavaScript in the controlled browser page. This is a normal browser automation/debugging capability, but it is powerful.

Skill content
agent-browser eval "document.title" ... agent-browser eval -b "<base64>" # Any JavaScript ... agent-browser eval --stdin
Recommendation

Only run page scripts you understand and keep this capability scoped to the site and task the user requested.

What this means

Browser sessions may remain open with cookies, tabs, or other state unless closed or cleaned up.

Why it was flagged

The browser process is intentionally kept alive between CLI commands. This is disclosed and useful for automation, but users should know it may outlive one command.

Skill content
The browser persists between commands via a background daemon
Recommendation

Close sessions when finished and avoid leaving authenticated browser automation sessions running unattended.

What this means

Saved browser state may carry sensitive account data or stale/poisoned site state into future automation runs.

Why it was flagged

The skill persists browser state across tasks. That is expected for authenticated automation, but the stored state can include sensitive data and can be reused later.

Skill content
Save cookies, storage, and auth state ... State File Contents ... "cookies" ... "localStorage" ... "sessionStorage"
Recommendation

Use separate named sessions per site/task, encrypt state where supported, keep state files out of source control, and delete them when no longer needed.

What this means

Users must trust the external agent-browser package source and whatever version their package manager or npx resolves.

Why it was flagged

The skill relies on an external CLI but the registry metadata does not provide source/homepage provenance or a pinned install specification.

Skill content
Source: unknown; Homepage: none; No install spec — this is an instruction-only skill.
Recommendation

Verify the package publisher/source before installing, prefer pinned versions, and avoid running npx for sensitive authenticated sessions unless provenance is clear.