Skills agent-browser

📦

agent-browser

Content revision r2 High Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Automate Browser Tasks with Agent Browser

Manual browser workflows are slow and difficult to reproduce. This skill drives remote Playwright sessions for navigation, interaction, extraction, screenshots, and video.

Supports: Claude Codex Code(CC)

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "agent-browser" from https://skillstore.io/skills/infsh-skills-agent-browser.md and its manifest at https://skillstore.io/api/skills/infsh-skills-agent-browser/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/infsh-skills-agent-browser.md Signed manifest GET /api/skills/infsh-skills-agent-browser/manifest Signed lockfile GET /api/skills/infsh-skills-agent-browser/lockfile

Test it

Using "agent-browser". Inspect the contact page and list available form controls without changing anything.

Expected outcome:

Page title: Contact
Available controls: name, email, message, consent checkbox, and submit button.
No fields were changed and the session was closed.

Using "agent-browser". Capture the public article page and summarize its visible content.

Expected outcome:

The page contains one article, five section headings, twelve links, and a full-page screenshot. The session is closed.

Using "agent-browser". Fill the approved test form and pause before submission.

Expected outcome:

The requested fields are filled. Submission is paused until explicit confirmation is provided.

Security Audit

High Risk

v5 • 8/6/2026 Open versioned report

Most static hits are false positives caused by Markdown syntax, fenced shell examples, placeholder URLs, relative links, and /dev/null redirection. Confirmed risks include external installation, remote image loading, TOTP exposure through process arguments, and remote screen capture. Credential submission, cookie extraction, local file upload, and page JavaScript require explicit consent and strict scoping.

10

Files scanned

2,315

Lines analyzed

3

Review items

0

False positives ignored

Confirmed security concerns (5)

High

Screen capture upload

description: "Browser automation for AI agents via inference.sh. Navigate web pages, interact with e

The declared capability captures screenshots and videos through the inference.sh service. Captured pages may contain credentials, personal data, or authenticated content sent to remote infrastructure.

High

SKILL.md:11 references/authentication.md:31-38 references/authentication.md:99-102 references/authentication.md:131-138

Credentials Sent Through Remote Browser Commands

Authentication examples submit passwords and TOTP codes through inference.sh browser commands, exposing secrets to a third-party execution boundary.

The cited commands explicitly place password and TOTP values into interactions handled by the inference.sh browser service.

High

references/authentication.md:209-219

Session Cookie Disclosure

The authentication guide extracts document.cookie from an authenticated page and prints the result, which can expose reusable session credentials in logs.

The guide explicitly evaluates document.cookie, stores the result, and echoes it under the Cookies label.

High

SKILL.md:158-167

Local File Disclosure Through Upload

The upload action accepts local file paths and sends those files through the remote browser to a website without an explicit confirmation requirement.

The example directly supplies an absolute local file path to the upload action, and the skill states that execution occurs through inference.sh.

Medium

SKILL.md:182-190

Arbitrary Page JavaScript Execution

The skill exposes page-context JavaScript execution, which can read sensitive page data or trigger state changes beyond element-based interactions.

The documented execute function accepts custom JavaScript and returns its result, establishing direct page-context code execution.

Capability review items (3)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium

references/authentication.md:133

Shell command substitution

TOTP_CODE=$(oathtool --totp -b "$TOTP_SECRET")

The example passes TOTP_SECRET to oathtool as a command-line argument. Other local users or process-monitoring tools may observe the secret.

Medium

Ruby/shell backtick execution

> **Install the belt CLI skill:** `npx skills add belt-sh/cli`

Although Markdown backticks do not execute code, this line explicitly directs users to run npx and install an external skill. That creates a real supply-chain execution boundary.

Low

Hardcoded URL

![Agentic Browser](https://cloud.inference.sh/app/files/u/4mg21r6ta37mpaz6ktzwtt8krr/01kgjw8atdxgkrs

This Markdown image loads from cloud.inference.sh when rendered. The request discloses viewer network metadata to an external host and depends on mutable remote content.

Risk Factors

⚙️ External commands (50)

references/authentication.md:24-26 references/authentication.md:51 references/authentication.md:52 references/authentication.md:70-72 references/authentication.md:80 references/authentication.md:97 references/authentication.md:115 references/authentication.md:116 references/authentication.md:128 references/authentication.md:129 references/authentication.md:133 references/authentication.md:153-156 references/authentication.md:179-181 references/authentication.md:202 references/authentication.md:215-217 references/authentication.md:218 references/authentication.md:222-223 references/authentication.md:243 references/authentication.md:246 references/authentication.md:285 references/authentication.md:292 references/authentication.md:21 references/authentication.md:68 references/authentication.md:174 references/proxy-support.md:22-25 references/proxy-support.md:35-40 references/proxy-support.md:65-68 references/proxy-support.md:76 references/proxy-support.md:107 references/proxy-support.md:111 references/proxy-support.md:113-116 references/proxy-support.md:119-121 references/proxy-support.md:137-142 references/proxy-support.md:150-153 references/proxy-support.md:186-189 references/proxy-support.md:192-194 references/proxy-support.md:195 references/proxy-support.md:267-270 references/proxy-support.md:273 references/proxy-support.md:294 references/proxy-support.md:50 references/proxy-support.md:90 references/session-management.md:33-35 references/session-management.md:36 references/session-management.md:89-91 references/session-management.md:92 references/session-management.md:94-96 references/session-management.md:97 references/session-management.md:140-142 references/session-management.md:154

🌐 Network access (50)

references/authentication.md:25 references/authentication.md:71 references/authentication.md:154 references/authentication.md:180 references/authentication.md:194 references/commands.md:25 references/commands.md:56 references/proxy-support.md:23 references/proxy-support.md:24 references/proxy-support.md:36 references/proxy-support.md:37 references/proxy-support.md:54 references/proxy-support.md:55 references/proxy-support.md:56 references/proxy-support.md:66 references/proxy-support.md:94 references/proxy-support.md:95 references/proxy-support.md:96 references/proxy-support.md:100 references/proxy-support.md:101 references/proxy-support.md:102 references/proxy-support.md:138 references/proxy-support.md:139 references/proxy-support.md:151 references/proxy-support.md:161 references/proxy-support.md:162 references/proxy-support.md:175 references/proxy-support.md:187 references/proxy-support.md:188 references/proxy-support.md:252 references/proxy-support.md:259 references/proxy-support.md:152 references/proxy-support.md:165 references/proxy-support.md:168 references/session-management.md:34 references/session-management.md:47 references/session-management.md:90 references/session-management.md:95 references/session-management.md:141 references/session-management.md:187 references/video-recording.md:24 references/video-recording.md:49 references/video-recording.md:88 references/video-recording.md:120 references/video-recording.md:198 SKILL.md:11 SKILL.md:13 SKILL.md:17 SKILL.md:23 SKILL.md:39

📁 Filesystem access (17)

references/authentication.md:5 references/authentication.md:263 references/commands.md:3 references/commands.md:59 references/proxy-support.md:5 references/proxy-support.md:272 references/session-management.md:5 references/session-management.md:136 references/snapshot-refs.md:5 references/video-recording.md:5 references/video-recording.md:239 templates/authenticated-session.sh:30 templates/capture-workflow.sh:28 templates/capture-workflow.sh:78 templates/capture-workflow.sh:81 templates/capture-workflow.sh:149 templates/form-automation.sh:23

Detected Patterns

Screen capture upload

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Security Assessment

Copy report link

https://skillstore.io/skills/infsh-skills-agent-browser/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/infsh-skills-agent-browser/security.svg)](https://skillstore.io/skills/infsh-skills-agent-browser?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/infsh-skills-agent-browser?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/infsh-skills-agent-browser/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/infsh-skills-agent-browser.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

infsh-skills. (2026). agent-browser security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/infsh-skills-agent-browser/audits/5

BibTeX citation

@techreport{infsh-skills-infsh-skills-agent-browser-2026,
  author = {infsh-skills},
  title = {agent-browser security audit report (audit version 5)},
  institution = {Skillstore},
  year = {2026},
  number = {5},
  url = {https://skillstore.io/skills/infsh-skills-agent-browser/audits/5},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "agent-browser security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
  - name: "infsh-skills"
date-released: "2026-08-06"
url: "https://skillstore.io/skills/infsh-skills-agent-browser/audits/5"
identifiers:
  - type: other
    value: "skillstore:infsh-skills-agent-browser:audit:5"
    description: "Skillstore immutable audit report identifier"

Compare variants

19 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

supercent-io Recommended

supercent-io-agent-browser

Skillstore Score 78

Evidence Confidence High

Skillstore usage 30

Updated

2026-08-21

101-skills-agent-browser

Skillstore Score 74

Evidence Confidence Medium

Skillstore usage 1

Updated

2026-08-21

vercel-labs-agent-browser

Skillstore Score 38

Evidence Confidence High

Skillstore usage 66

Updated

2026-08-21

qu-skills-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 40

Updated

2026-08-21

am-will-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 36

Updated

2026-08-21

tul-sh-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 35

Updated

2026-08-21

inference-sh-8-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 25

Updated

2026-08-21

toolshell-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 16

Updated

2026-08-21

skillssh-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 16

Updated

2026-08-21

inference-sh-9-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 15

Updated

2026-08-21

inferen-sh-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

inference-shell

inference-shell-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

inferencesh-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

inference-sh-skills

inference-sh-skills-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

inference-sh-0-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

infsh-skills Current

infsh-skills-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

inf-sh-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

inference-skills

inference-skills-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 6

Updated

2026-08-21

halt-catch-fire

halt-catch-fire-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 3

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

45

Architecture

85

Maintainability

87

Content

69

Community

83

Spec Compliance

What You Can Build

Inspect Web Interfaces

Open a page, identify interactive elements, and capture current state before making changes.

Collect Public Page Data

Extract visible text, links, titles, and screenshots from approved public websites.

Automate Repeated Form Workflows

Fill and verify approved forms with controlled inputs and confirmation before submission.

Try These Prompts

Inspect a Page

Open [URL], return the page title and interactive elements, then stop without clicking or entering data.

Capture Public Content

Open [URL], extract the main visible text and links, take a full-page screenshot, then close the session.

Prepare a Form Submission

Open [FORM URL], map fields to my provided values, fill them, and ask for confirmation before submitting.

Run a Scoped Browser Workflow

Use [PROXY] to inspect [URL], perform only [ALLOWED ACTIONS], record video, extract [FIELDS], and close every session.

Best Practices

Use approved domains, disposable test accounts, and the minimum required permissions.
Refresh element references after navigation, form submission, or dynamic content changes.
Confirm before uploads, submissions, authentication, recording, or JavaScript execution.

Avoid

Do not capture credentials, payment data, private messages, or confidential pages without authorization.
Do not reuse stale element references after the page changes.
Do not leave sessions open or store cookies, screenshots, videos, and extracted data indefinitely.

Frequently Asked Questions

What must be installed?

The inference.sh CLI and its agent-browser service are required. Authentication and network access are also necessary.

Does this skill run a local browser?

No. The documented workflow sends commands to agent-browser through inference.sh.

Why do element references stop working?

Navigation and dynamic page changes invalidate references. Request a new snapshot before continuing.

Can it work with authenticated pages?

Yes, but credentials and page data may cross a remote service boundary. Use approved test accounts and explicit consent.

Can it upload local files?

Yes. Confirm the exact file and destination first, and restrict uploads to approved paths and domains.

How should sessions be closed?

Call the close function after every workflow. Closing also returns recorded video when recording is enabled.

Developer Details

Author

License

MIT

Skillstore revision

r2

Version notice

The author did not declare a version.

Repository

https://github.com/infsh-skills/skills/tree/main/tools/utilities/agent-browser/

Ref

4121de961d1b6f2ffca856260e239505c302452c

Maintenance freshness

8/7/2026

Usage

6 downloads · 118 views

File structure

📁 references/

📄 authentication.md

📄 commands.md

📄 proxy-support.md

📄 session-management.md

📄 snapshot-refs.md

📄 video-recording.md

📁 templates/

📄 authenticated-session.sh

📄 capture-workflow.sh

📄 form-automation.sh

More from infsh-skills

remotion-render

Render React Animations as Videos

Creating polished video from React animation code requires a reliable rendering workflow. This skill sends Remotion TSX to inference.sh and returns a rendered video.

Design & Creative View

ai-avatar-video

Create AI Avatar and Talking Head Videos

Producing presenter videos requires coordinated image, speech, and lip sync tools. This skill builds inference.sh workflows for avatars, localization, and batch content.

Design & Creative View

ai-image-generation

Generate and Edit Images with AI

Choosing and invoking image models can require repeated CLI research. This skill provides model guidance and ready workflows for generation, editing, upscaling, and stitching.

Design & Creative View

web-search

Search and Extract Web Content with Tavily and Exa

Finding current information and extracting useful page content often requires separate tools. This skill provides documented Tavily and Exa workflows through the belt CLI.

Research & Learning View

ai-video-generation

Create AI Videos with Inference Models

Choosing and invoking video models can require extensive platform knowledge. This skill provides model guidance and adaptable belt CLI workflows.

Design & Creative View

twitter-automation

Automate Twitter and X Account Actions

Managing routine X actions across separate tools takes time and creates inconsistent workflows. This skill provides focused CLI commands for publishing, engagement, messaging, and retrieval.

Communication View

playwright-testing

Build Reliable Playwright Tests

by C0ntr0lledCha0s

Playwright test suites can become flaky, slow, and difficult to maintain. This skill provides practical patterns for locators, fixtures, page objects, debugging, mocking, and configuration.

Coding & Development View

webapp-testing

Create Playwright Web App Tests

by AutumnsGrove

Manual browser testing is slow and often misses regressions across forms, devices, and network states. This skill helps Claude, Codex, and Claude Code create practical Playwright tests for real web workflows.

Coding & Development View

firecrawl-build-interact

Build Firecrawl Browser Interactions

by firecrawl

Dynamic pages often hide data behind clicks, forms, and login flows. This skill helps teams choose and scope Firecrawl /interact integrations.

Coding & Development View

playwright-best-practices

Improve Playwright Test Reliability

by 0xBigBoss

Playwright tests often become flaky, slow, and noisy in agent workflows. This skill provides concise patterns for locators, assertions, fixtures, auth reuse, network mocks, and compact reporters.

Coding & Development View

e2e-testing

Build Reliable Playwright E2E Workflows

by sickn33

End-to-end coverage becomes inconsistent when setup, browser checks, visual tests, and CI integration are planned separately. This skill organizes them into one Playwright workflow.

Coding & Development View

testing

Build Reliable Test Automation

by 89jobrien

Weak tests slow releases and hide regressions. This skill guides test strategy, TDD, automation, coverage review, and Playwright web checks.

Coding & Development View