Agent Browser 0.2.0

PassAudited by ClawScan on May 10, 2026.

Overview

This is a coherent browser-automation wrapper, but it relies on an external CLI that can interact with websites and handle browser session data.

Install this only if you trust the upstream agent-browser CLI. Use it for explicit browser automation tasks, be careful on logged-in or sensitive websites, confirm important actions before submission, and clear browser cookies/storage when finished.

Findings (4)

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

If used on sensitive sites, the agent could perform real web actions such as changing settings, submitting forms, or uploading a selected file.

Why it was flagged

The skill grants the agent access to a broad browser automation CLI. This matches the purpose, but the commands can click, type, submit, and upload files on websites.

Skill content
allowed-tools: Bash(agent-browser:*) ... agent-browser click @e1 ... agent-browser fill @e2 "text" ... agent-browser upload @e1 file.pdf
Recommendation

Use it for clearly requested browser tasks, and review/confirm actions before account changes, purchases, posts, deletions, or file uploads.

What this means

The behavior ultimately depends on the installed agent-browser package, not just this skill documentation.

Why it was flagged

The actual executable is installed from npm or built from GitHub, and the reviewed skill contains no code files for that CLI. This is normal for a wrapper skill, but users are trusting the external package/source.

Skill content
npm install -g agent-browser
agent-browser install
agent-browser install --with-deps ... git clone https://github.com/vercel-labs/agent-browser
cd agent-browser
pnpm install
pnpm build
Recommendation

Install only from a trusted package/source, consider pinning a known version, and verify the upstream project before using it with important accounts or data.

What this means

If credentials are used on the wrong site or exposed in command history/output, protected account access could be affected.

Why it was flagged

The CLI can be given HTTP Basic Auth credentials. That is expected for browser automation, but credentials grant access to protected sites.

Skill content
agent-browser set credentials user pass   # HTTP basic auth
Recommendation

Only provide credentials for intended sites, avoid sharing secrets in prompts when possible, and clear or rotate credentials if they may have been exposed.

What this means

Session data from one browsing task could be visible in outputs or reused in later browser actions.

Why it was flagged

The browser context can retain and expose cookies or localStorage. This is useful for logged-in automation, but those values may include sensitive session data.

Skill content
Recording creates a fresh context but preserves cookies/storage from your session ... agent-browser cookies                     # Get all cookies
agent-browser storage local               # Get all localStorage
Recommendation

Use separate browser contexts for sensitive work, avoid unnecessary cookie/storage inspection, and clear cookies/storage after tasks involving private accounts.