Skills agent-browser

📦

agent-browser

Name: agent-browser
Author: skillssh

Content revision r1 High Risk ⚙️ External commands🌐 Network access📁 Filesystem access

Automate Browser Sessions with Element Refs

Manual browser workflows are slow to repeat and hard for agents to control. This skill routes actions through inference.sh with element refs, screenshots, video, and session state.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

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/skillssh-agent-browser.md and its manifest at https://skillstore.io/api/skills/skillssh-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/skillssh-agent-browser.md Signed manifest GET /api/skills/skillssh-agent-browser/manifest Signed lockfile GET /api/skills/skillssh-agent-browser/lockfile

Test it

Using "agent-browser". Inspect a product settings page and identify available actions.

Expected outcome:

The session opened successfully. The page contains settings tabs, save and cancel buttons, a notification toggle, and a billing link. A fresh snapshot is needed after changing tabs.

Using "agent-browser". Submit a contact form and capture evidence.

Expected outcome:

The form was filled and submitted. The final page shows a success message, and a full-page screenshot was saved for review.

Using "agent-browser". Record a short workflow for documentation.

Expected outcome:

The workflow was recorded from page load through the save action. The session was closed and the recording file was returned.

Security Audit

High Risk

v4 • 7/7/2026 Open versioned report

Most static findings are false positives from Markdown examples, shell templates, relative links, and /dev/null redirects. Confirmed risk remains for hosted browser capture, SOCKS proxy support, cookie extraction guidance, proxy rotation for rate-limit avoidance, and arbitrary JavaScript execution on browsed pages.

Files scanned

2,108

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (4)

High

SKILL.md:3

Screen capture upload

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

The skill description advertises screenshots, video recording, and file upload through a hosted browser service. These capabilities can expose sensitive page contents or local files if used on private sessions.

High

references/authentication.md:209-224

Cookie Extraction Guidance

The authentication documentation includes a workflow that reads document.cookie and prints cookies from an authenticated session. This can expose session tokens to logs or downstream tools.

The cited section is explicitly titled Cookie Extraction and shows cookie values being captured and echoed. That is a direct session-data exposure risk.

High

references/proxy-support.md:85-128

Proxy Rotation for Rate Limit Avoidance

The proxy documentation labels a workflow as rate limit avoidance and demonstrates rotating proxies during scraping. This can enable evasion of service controls.

The section title and example directly describe rotating proxies for web scraping under rate limit avoidance. The abuse intent is clear from the surrounding text.

Medium

references/commands.md:162-176 templates/capture-workflow.sh:103-117

Arbitrary Page JavaScript Execution

The skill exposes an execute function for running JavaScript in the current page and templates use it to extract page text and links. This can reveal data from authenticated pages.

The command reference defines arbitrary JavaScript execution, and the capture template uses it for DOM extraction. The capability is legitimate but sensitive.

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.

High

references/proxy-support.md:152

SOCKS proxy

"proxy_url": "socks5://privacy-proxy.example.com:1080"

The documentation explicitly supports SOCKS proxy routing for browser traffic. This can anonymize scraping activity and bypass network or site controls when misused.

High

references/proxy-support.md:165

SOCKS proxy

### SOCKS5 Proxy

The documentation explicitly supports SOCKS proxy routing for browser traffic. This can anonymize scraping activity and bypass network or site controls when misused.

High

references/proxy-support.md:168

SOCKS proxy

{"proxy_url": "socks5://proxy.example.com:1080"}

The documentation explicitly supports SOCKS proxy routing for browser traffic. This can anonymize scraping activity and bypass network or site controls when misused.

Risk Factors

⚙️ External commands (163)

🌐 Network access (54)

📁 Filesystem access (15)

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/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

Copy report link

https://skillstore.io/skills/skillssh-agent-browser/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/skillssh-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

skillssh. (2026). agent-browser security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/skillssh-agent-browser/audits/4

BibTeX citation

@techreport{skillssh-skillssh-agent-browser-2026,
  author = {skillssh},
  title = {agent-browser security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/skillssh-agent-browser/audits/4},
  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 4)"
version: "unspecified"
type: report
authors:
  - name: "skillssh"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/skillssh-agent-browser/audits/4"
identifiers:
  - type: other
    value: "skillstore:skillssh-agent-browser:audit:4"
    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

101-skills-agent-browser

Skillstore Score 74

Evidence Confidence Medium

Skillstore usage 1

Updated

2026-08-21

vercel-labs

vercel-labs-agent-browser

Skillstore Score 38

Evidence Confidence High

Skillstore usage 66

Updated

2026-08-21

qu-skills

qu-skills-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 40

Updated

2026-08-21

am-will

am-will-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 36

Updated

2026-08-21

tul-sh

tul-sh-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 35

Updated

2026-08-21

inference-sh-8

inference-sh-8-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 25

Updated

2026-08-21

toolshell

toolshell-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 16

Updated

2026-08-21

skillssh Current

skillssh-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 16

Updated

2026-08-21

inference-sh-9

inference-sh-9-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 15

Updated

2026-08-21

inferen-sh

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

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

inference-sh-0-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

infsh-skills

infsh-skills-agent-browser

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 8

Updated

2026-08-21

inf-sh

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

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Validate Web Flows

Run repeatable browser checks for login screens, forms, navigation paths, and visual states.

Capture Web Evidence

Collect screenshots, page text, links, and session videos for research or documentation tasks.

Operate Authenticated Pages

Use a persistent session to inspect dashboards and complete authorized browser actions.

Try These Prompts

Open and Inspect a Page

Open the target URL with agent-browser. Summarize the page title, visible interactive elements, and any elements that need a fresh snapshot.

Fill a Simple Form

Open the form URL, identify the refs for each field, fill the provided values, submit the form, and verify the result with a new snapshot.

Capture Documentation Assets

Record a browser session for this workflow, use pauses between major actions, capture a full-page screenshot, and close the session to retrieve the recording.

Extract Authorized Page Data

Use the execute function only on the authorized page. Extract visible headings, links, and table text, then report the data sources and any sensitive fields skipped.

Best Practices

Refresh the snapshot after navigation, form submission, modal changes, or dynamic content updates.
Use recording and screenshots only when the page does not show credentials or private data.
Close sessions after work completes to limit retained browser state and captured artifacts.

Avoid

Do not reuse old element refs after the page changes.
Do not use proxy rotation to evade rate limits or site access rules.
Do not extract cookies, tokens, passwords, or personal data from authenticated pages.