Automate Browser Workflows with Agent Browser
Manual browser tasks slow down research, testing, and form workflows. This skill uses inference.sh sessions to navigate pages, interact with elements, capture evidence, and extract page content.
Do not auto-install this skill.
The canonical policy requires operator review before any installation action.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "agent-browser" from https://skillstore.io/skills/inference-sh-8-agent-browser.md and its manifest at https://skillstore.io/api/skills/inference-sh-8-agent-browser/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "agent-browser". Inspect a public landing page and list its interactive elements.
Expected outcome:
The page opened successfully. It includes a search field, pricing link, documentation link, and sign-in button.
Using "agent-browser". Submit a contact form with approved test data.
Expected outcome:
The form was filled and submitted. The final page displayed a thank-you message and no validation errors.
Using "agent-browser". Capture a product settings workflow for documentation.
Expected outcome:
Screenshots were captured for the settings page, edit action, save action, and final confirmation state.
Most static findings are false positives from Markdown syntax, visible shell examples, placeholder URLs, relative documentation links, and /dev/null redirection. Confirmed risks include the remote installer piped to shell, advertised screen capture and file upload capabilities, SOCKS proxy support, cookie extraction guidance, proxy-based rate limit avoidance, and automated authentication handling.
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/inference-sh-8-agent-browser/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/inference-sh-8-agent-browser?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/inference-sh-8-agent-browser?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-8-agent-browser/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/inference-sh-8-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>inference-sh-8. (2026). agent-browser security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-8-agent-browser/audits/4@techreport{inference-sh-8-inference-sh-8-agent-browser-2026,
author = {inference-sh-8},
title = {agent-browser security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-sh-8-agent-browser/audits/4},
note = {Author version unspecified}
}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: "inference-sh-8"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/inference-sh-8-agent-browser/audits/4"
identifiers:
- type: other
value: "skillstore:inference-sh-8-agent-browser:audit:4"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
supercent-io-agent-browser
2026-08-21
101-skills-agent-browser
2026-08-21
vercel-labs-agent-browser
2026-08-21
qu-skills-agent-browser
2026-08-21
am-will-agent-browser
2026-08-21
tul-sh-agent-browser
2026-08-21
inference-sh-8-agent-browser
2026-08-21
toolshell-agent-browser
2026-08-21
skillssh-agent-browser
2026-08-21
inference-sh-9-agent-browser
2026-08-21
inferen-sh-agent-browser
2026-08-21
inference-shell-agent-browser
2026-08-21
inferencesh-agent-browser
2026-08-21
inference-sh-skills-agent-browser
2026-08-21
inference-sh-0-agent-browser
2026-08-21
infsh-skills-agent-browser
2026-08-21
inf-sh-agent-browser
2026-08-21
inference-skills-agent-browser
2026-08-21
halt-catch-fire-agent-browser
2026-08-21
Run repeatable browser actions, capture screenshots, and record videos for failed test cases.
Open public pages, collect visible text, save links, and document the page state.
Record guided browser sessions and capture screenshots for help articles or process reviews.
Open this URL with agent-browser. Summarize the page title, visible form fields, main links, and available buttons.
Use agent-browser to inspect this form. Fill the fields I provide, submit it, and report the confirmation state.
Navigate this workflow with agent-browser. Take a full page screenshot at each major step and describe what changed.
Use agent-browser to open these pages, extract visible text and links, and compare the results in a concise table.
Author
inference-sh-8License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a06681402992ceae98ba04d54cfd4ab004862696
Maintenance freshness
7/18/2026
Usage
23 downloads · 223 views
File structure
Generate AI Images with inference.sh
Creating model-specific image prompts and commands can slow visual work. This skill provides inference.sh examples for generation, editing, upscaling, and model selection.
Automate Twitter/X Workflows
Manual Twitter/X posting and engagement can slow repeatable social workflows. This skill guides Claude, Codex, and Claude Code through inference.sh CLI actions for posts, media, DMs, follows, and lookups.
Render Remotion Videos from React Code
Creating animated videos from React components is hard to package and render reliably. This skill sends Remotion TSX to inference.sh and returns an MP4 render.
Create AI Video Workflows
AI video tasks require matching prompts, models, and CLI options. This skill guides inference.sh video generation, animation, lipsync, upscaling, and media merging.
Run AI Apps with inference.sh
Teams need one CLI workflow for many hosted AI models and media tools. This skill helps Claude, Codex, and Claude Code discover apps, run tasks, and track results.
Automate Browser Tasks with Delegated DevTools
by 727474430
Browser work can flood the main chat with page state, screenshots, and request logs. This skill delegates those tasks to a Chrome DevTools agent and returns concise results.
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.
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.
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.
Build Firecrawl Single-Page Scraping
by firecrawl
Apps often need clean content from one known URL. This skill guides a focused Firecrawl /scrape integration for page extraction.
Improve QA Coverage for Web Apps
by alirezarezvani
Modern teams need clear test strategy and practical automation without slowing delivery. This skill helps Claude, Codex, and Claude Code plan tests, review coverage, and scaffold QA workflows.