Skip to content
TrustedSkillsbeta
Back to all skills

Agent Browser

Official
vercel-labs·vlatest·cloud·MIT

Automates web tasks, data extraction, and content creation using a browser interface powered by Vercel's AI infrastructure.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add vercel-labs/open-agents --skill agent-browser -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

vercel-labs

Matched to the vendor's own GitHub organisation.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 1 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 3 hosts that are neither well-known infrastructure nor declared in the skill's frontmatter: corpproxy.company.com, httpbin.org, proxy.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    proxy.comundeclaredcorpproxy.company.comundeclaredhttpbin.orgundeclared

    What it found (3 of 4)

    • .agents/skills/agent-browser/SKILL.md:241contacts proxy.com
      agent-browser --proxy http://proxy.com:8080 open example.com
    • .agents/skills/agent-browser/references/proxy-support.md:121contacts corpproxy.company.com
      export HTTP_PROXY="http://corpproxy.company.com:8080"
    • .agents/skills/agent-browser/references/proxy-support.md:122contacts corpproxy.company.com
      export HTTPS_PROXY="http://corpproxy.company.com:8080"

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned vercel-labs/open-agents at cf865e94de.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
cf865e94de
Manifest
.agents/skills/agent-browser/SKILL.md
Scanned
9 files, 1,259 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The vercel-labs/agent-browser skill enables AI agents to interact with web pages, extract information, and perform actions within a browser environment. It allows agents to navigate websites, fill out forms, click buttons, and scrape data – effectively extending their capabilities beyond simple text processing. This provides the agent with visual context and the ability to complete tasks requiring real-time interaction with online services.

When to use it

  • Data Extraction: Automatically gather product details, pricing, or other information from e-commerce websites.
  • Form Filling: Populate online forms for applications, registrations, or data submissions.
  • Web Automation: Automate repetitive tasks like booking appointments or managing social media accounts.
  • Research & Summarization: Gather and summarize content from multiple web pages related to a specific topic.

Key capabilities

  • Browser navigation
  • Form interaction (filling, submission)
  • Clicking elements on webpages
  • Data scraping/extraction

Example prompts

  • "Go to https://www.example.com and extract the title of the page."
  • "Fill out this form at https://www.formsite.com/contact with my details: [details]."
  • "Click the 'Submit' button on this webpage: https://www.example.com/checkout."

Tips & gotchas

  • The agent may require explicit instructions for navigating complex websites or interacting with dynamic content.
  • Be mindful of website terms of service and robots.txt when scraping data.