Automate Browser Tasks with AI Agents
Web tasks often require repeated navigation, form entry, and visual checks. This skill gives Claude, Codex, and Claude Code a structured browser workflow through inference.sh.
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-0-agent-browser.md and its manifest at https://skillstore.io/api/skills/inference-sh-0-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 pricing page and capture visible calls to action.
Expected outcome:
Using "agent-browser". Fill a test contact form with approved sample data.
Expected outcome:
Using "agent-browser". Record a short workflow for a documentation review.
Expected outcome:
The skill provides useful browser automation, but it relies on shell-driven infsh workflows, remote browser capture, proxy support, file upload, and page JavaScript execution. The critical issue is the pipe-to-shell installer; additional high-risk content includes cookie extraction guidance and proxy rotation for rate-limit avoidance. No prompt injection attempt was found in the reviewed files.
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-0-agent-browser/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/inference-sh-0-agent-browser?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/inference-sh-0-agent-browser?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/inference-sh-0-agent-browser/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/inference-sh-0-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-0. (2026). agent-browser security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/inference-sh-0-agent-browser/audits/4@techreport{inference-sh-0-inference-sh-0-agent-browser-2026,
author = {inference-sh-0},
title = {agent-browser security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/inference-sh-0-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-0"
date-released: "2026-07-05"
url: "https://skillstore.io/skills/inference-sh-0-agent-browser/audits/4"
identifiers:
- type: other
value: "skillstore:inference-sh-0-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 verify visible results after each step.
Open public pages, extract visible text and links, and save screenshots for review.
Navigate authenticated tools, fill forms, and record selected workflows after explicit approval.
Open this URL with agent-browser, capture the visible page state, and summarize the main interactive elements: [URL]
Use agent-browser to inspect this form, identify the needed @e refs, fill the approved values, submit it, and report the result: [URL]
Run this approved browser workflow, take screenshots after key steps, and explain any failed action without retrying destructive steps: [WORKFLOW]
After I confirm the target and credentials, use agent-browser to perform the approved authenticated checks, avoid recording secrets, and close the session when done.
Author
inference-sh-0License
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
a25199bc7d6b82598536822d1738eb5d5f54025b
Maintenance freshness
7/18/2026
Usage
8 downloads · 190 views
File structure
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.
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 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.
Review Code for Security, Quality, and Performance
by AutumnsGrove
Manual reviews can miss security, quality, and performance issues. This skill applies a structured workflow and optional analysis tools to produce prioritized feedback.
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.