Skills agent-browser

📦

agent-browser

Name: agent-browser
Author: qu-skills

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

Automate Browser Workflows

Manual browser tasks are slow to repeat and difficult to document. This skill gives Claude, Codex, and Claude Code structured browser control with refs, screenshots, video, and reusable shell templates.

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

Test it

Using "agent-browser". Open a product settings page and report the available controls.

Expected outcome:

A concise page summary with named refs for buttons, inputs, links, and a screenshot reference for visual review.

Using "agent-browser". Submit a contact form with test data and verify the result.

Expected outcome:

A step-by-step status report showing filled fields, submission status, and the visible confirmation message.

Using "agent-browser". Capture evidence for a failed checkout flow.

Expected outcome:

A written failure summary with the final page URL, visible error message, screenshot reference, and optional video reference.

Security Audit

High Risk

v4 • 7/6/2026 Open versioned report

Most static shell, URL, path, and device findings are documentation examples or benign shell redirections. Real risks come from screen capture, video, SOCKS proxies, JavaScript execution, file upload, proxy rotation, and cookie extraction. No prompt injection attempt was found in the reviewed skill files.

Files scanned

2,110

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (5)

High

SKILL.md:3

Screen capture upload

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

The skill explicitly supports screenshots and video recordings of browser sessions. These artifacts can include sensitive page content and are returned as files.

High

references/proxy-support.md:85-128

Rate-Limit Evasion Guidance

The proxy guide recommends rotating proxies for "Rate Limit Avoidance" during web scraping. This can enable automated policy evasion across target sites.

The section title and surrounding example directly describe rotating proxies to avoid rate limits. This is explicit abuse-enabling guidance, not a weak keyword match.

High

references/authentication.md:209-224

Session Cookie Exposure Guidance

The authentication guide shows extracting document.cookie and printing cookies. This can expose session tokens or allow copying authenticated state outside the browser.

The cited section is specifically titled Cookie Extraction and echoes cookie values. The risk is clear for authenticated sessions.

High

SKILL.md:182-190 references/commands.md:162-176

Arbitrary Page JavaScript Execution

The skill exposes an execute function that runs custom JavaScript in the page context. In authenticated sessions, this can read page data or trigger page actions.

The execute capability is explicitly documented and accepts caller-supplied JavaScript. The risk depends on target permissions, but the capability is real.

High

SKILL.md:158-167 references/commands.md:95-98

Local File Upload Capability

The upload action accepts file paths and sends selected files to page inputs. Without strict user approval, this could transmit sensitive local files.

The capability is clearly documented as file upload with file_paths. The finding is contextual because safe use is possible with explicit allowlists.

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 SOCKS5 proxy routing for browser traffic. In context with privacy and rate-limit examples, this can enable anonymized or policy-evasive browsing.

High

references/proxy-support.md:165

SOCKS proxy

### SOCKS5 Proxy

The documentation explicitly supports SOCKS5 proxy routing for browser traffic. In context with privacy and rate-limit examples, this can enable anonymized or policy-evasive browsing.

High

references/proxy-support.md:168

SOCKS proxy

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

The documentation explicitly supports SOCKS5 proxy routing for browser traffic. In context with privacy and rate-limit examples, this can enable anonymized or policy-evasive browsing.

Risk Factors

⚙️ External commands (164)

🌐 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/qu-skills-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/qu-skills-agent-browser/security.svg)](https://skillstore.io/skills/qu-skills-agent-browser?utm_source=security_passport_badge)

HTML badge

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

Embed card

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

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

BibTeX citation

@techreport{qu-skills-qu-skills-agent-browser-2026,
  author = {qu-skills},
  title = {agent-browser security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/qu-skills-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: "qu-skills"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/qu-skills-agent-browser/audits/4"
identifiers:
  - type: other
    value: "skillstore:qu-skills-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 Current

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

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

Repeat Form Checks

Open a form, identify refs, submit test data, and capture screenshots for validation.

Capture Web Evidence

Record a user journey or capture full-page screenshots for bug reports and stakeholder review.

Extract Page Content

Collect visible text, links, titles, and screenshots from selected pages for structured research.

Try These Prompts

Open and Inspect a Page

Use agent-browser to open this URL, list the important interactive refs, and summarize the visible page state.

Fill a Test Form

Open this form, identify the required fields, fill them with safe test values, submit it, and capture the final page state.

Capture a Workflow

Record a browser session for this workflow, show the cursor, take a final screenshot, and close the session to retrieve the video.

Authenticated Data Review

After I provide approved credentials, use an authenticated browser session to review the dashboard, avoid recording secrets, and close the session.

Best Practices

Use only approved target sites and follow their terms and rate limits.
Keep credentials in secure environment variables and avoid recording sensitive sessions.
Refresh snapshots after navigation, form submission, or dynamic page changes.

Avoid

Do not run the skill against unknown sites while using real account credentials.
Do not upload local files unless the target site and file path are explicitly approved.
Do not use proxy rotation to bypass access controls, rate limits, or site policies.