📦

agent-browser

Name: agent-browser
Author: inference-skills

Revisión del contenido r1 Riesgo alto ⚙️ Comandos externos🌐 Acceso a red📁 Acceso al sistema de archivos

Automatiza flujos de trabajo del navegador con Agent Browser

Las tareas manuales del navegador ralentizan la investigación, las pruebas y el trabajo operativo. Esta skill proporciona a Claude, Codex y Claude Code sesiones de navegador repetibles con snapshots, acciones, capturas de pantalla y videos.

Compatible con: Claude Codex Code(CC)

⚠️ 38 Deficiente

Detente y solicita confirmación antes de instalar.

Revisa el plan y obtén el consentimiento explícito del usuario antes de modificar archivos.

Instalar con mi Agente

Copia esta solicitud en tu Agente. Incluye la página canónica del Skill y el manifiesto.

Solicitud de agente

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

Tu Agente debe seguir mostrando su plan y solicitar cualquier confirmación exigida por la política de seguridad.

Recursos legibles por agentes

Usa estos enlaces cuando un agente de IA, crawler o script necesite contexto limpio en vez de leer la página completa.

Detalle Markdown GET /skills/inference-skills-agent-browser.md Manifest firmado GET /api/skills/inference-skills-agent-browser/manifest Lockfile firmado GET /api/skills/inference-skills-agent-browser/lockfile

Pruébalo

Usando "agent-browser". Abre una página de producto y captura los elementos interactivos clave.

Resultado esperado:

Un breve resumen de la página, el título y la URL actuales, una referencia de captura de pantalla y los botones, enlaces y campos de formulario principales disponibles para actuar.

Usando "agent-browser". Envía un formulario de contacto de prueba y verifica el éxito.

Resultado esperado:

Un resultado paso a paso que muestra qué campos se rellenaron, si la acción de envío tuvo éxito, el estado final de la página y una captura de pantalla como evidencia.

Usando "agent-browser". Graba un flujo de trabajo de configuración para documentación.

Resultado esperado:

Un video de sesión completado, una captura de pantalla final y un resumen conciso de la ruta de navegación y el ajuste modificado.

Auditoría de seguridad

Riesgo alto

v4 • 6/7/2026 Abrir el informe versionado

Many static hits are false positives from Markdown code fences, relative documentation links, example URLs, and harmless /dev/null redirection. Confirmed risk remains significant because the skill runs an external browser automation CLI, supports screenshots, videos, file uploads, arbitrary page JavaScript, authenticated sessions, and SOCKS proxies. Additional semantic risks include cookie extraction guidance and proxy rotation for rate-limit avoidance.

Archivos escaneados

2,108

Líneas analizadas

Elementos de revisión

Falsos positivos ignorados

Preocupaciones de seguridad confirmadas (5)

Alto

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. Those capabilities can expose page contents or local files if used without explicit authorization.

Alto

references/authentication.md:209-224

Cookie Extraction Guidance

The authentication guide includes a workflow that reads document.cookie from an authenticated browser session and prints the cookie value. This can expose session material if copied into automation or logs.

The section is explicitly titled cookie extraction and assigns cookie data from a browser execute call before echoing it. That is strong evidence of sensitive session data exposure risk.

Alto

references/proxy-support.md:85-128

Proxy Rotation for Rate Limit Avoidance

The proxy documentation includes a section for rate limit avoidance that rotates proxies while fetching multiple pages. This can enable abuse of site anti-automation controls.

The section name and example behavior directly describe rotating proxies for rate limit avoidance. Legitimate scraping is possible, but the abuse-enablement signal is clear.

Alto

references/commands.md:162-176 SKILL.md:180-188

Arbitrary Page JavaScript Execution

The skill exposes an execute function that runs caller-provided JavaScript on the current page. This can read page content, manipulate authenticated pages, and extract sensitive DOM-accessible data.

Both the command reference and main skill file document caller-supplied JavaScript execution. The risk depends on target page authorization, but the capability is explicit.

Medio

references/video-recording.md:189-211

Sensitive Admin Session Recording

The video guide records an admin page workflow and archives the resulting video. Admin recordings can preserve sensitive page contents, identifiers, or operational actions if access controls are weak.

The example uses an admin URL and saves a recording for audit. This can be legitimate, but the evidence clearly shows sensitive workflow capture as a supported pattern.

Elementos de revisión de capacidades (59)

Estas son capacidades locales reales que pueden esperarse para esta habilidad, por lo que requieren revisión, pero no se cuentan como comportamiento malicioso confirmado.

Alto

references/proxy-support.md:152

SOCKS proxy

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

The documentation explicitly supports SOCKS proxy configuration for browser traffic. SOCKS proxy support can hide origin traffic or bypass network controls, so it is a real high-risk capability.

Alto

references/proxy-support.md:165

SOCKS proxy

### SOCKS5 Proxy

The documentation explicitly supports SOCKS proxy configuration for browser traffic. SOCKS proxy support can hide origin traffic or bypass network controls, so it is a real high-risk capability.

Alto

references/proxy-support.md:168

SOCKS proxy

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

The documentation explicitly supports SOCKS proxy configuration for browser traffic. SOCKS proxy support can hide origin traffic or bypass network controls, so it is a real high-risk capability.

Medio

references/authentication.md:24-26

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:51

Shell command substitution

RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:70-72

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:80

Shell command substitution

RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:97

Shell command substitution

RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:115

Shell command substitution

RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:128

Shell command substitution

RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:133

Shell command substitution

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

The line generates a TOTP code from a secret for automated login. This is legitimate authentication automation but handles sensitive credentials in shell.

Medio

references/authentication.md:153-156

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:179-181

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:202

Shell command substitution

SESSION=$(login)

This captures an authenticated session returned by the login helper in the surrounding workflow. The risk is contextual because it reuses browser authentication state.

Medio

references/authentication.md:215-217

Shell command substitution

RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:222-223

Shell command substitution

RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/authentication.md:243

Shell command substitution

export PASSWORD=$(cat /path/to/secure/password)

The example reads a password into an environment variable from a file or secrets manager. It is presented as a best practice, but it still handles credentials in shell context.

Medio

references/authentication.md:246

Shell command substitution

export PASSWORD=$(vault read -field=password secret/app)

The example reads a password into an environment variable from a file or secrets manager. It is presented as a best practice, but it still handles credentials in shell context.

Medio

references/proxy-support.md:22-25

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:35-40

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:65-68

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:76

Shell command substitution

RESULT=$(belt app run agent-browser --function snapshot --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:113-116

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:119-121

Shell command substitution

RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:137-142

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:150-153

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:186-189

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:192-194

Shell command substitution

RESULT=$(belt app run agent-browser --function execute --session $SESSION --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/proxy-support.md:267-270

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/snapshot-refs.md:124-126

Shell command substitution

RESULT=$(belt app run agent-browser --function interact --session $SESSION --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/snapshot-refs.md:136-138

Shell command substitution

RESULT=$(belt app run agent-browser --function interact --session $SESSION --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:23-26

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:38

Shell command substitution

RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:48-52

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:87-90

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:93-95

Shell command substitution

RESULT=$(belt app run agent-browser --function interact --session $SESSION --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:103

Shell command substitution

CLOSE_RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:119-124

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:156

Shell command substitution

RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:168-171

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:178

Shell command substitution

CLOSE_RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:197-200

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

references/video-recording.md:206

Shell command substitution

RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

SKILL.md:36-38

Shell command substitution

RESULT=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

SKILL.md:116-120

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

SKILL.md:215-217

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

SKILL.md:233-235

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

SKILL.md:248-251

Shell command substitution

SESSION=$(belt app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

SKILL.md:259

Shell command substitution

RESULT=$(belt app run agent-browser --function close --session $SESSION --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

templates/authenticated-session.sh:40-42

Shell command substitution

RESULT=$(infsh app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

templates/authenticated-session.sh:1

Unix shell invocation

#!/bin/bash

This is an executable shell template that runs the browser automation CLI and handles user-supplied URLs or sessions. It is legitimate functionality, but it is real external command execution.

Medio

templates/capture-workflow.sh:28

Shell command substitution

CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION_ID --input '{}' 2>/de

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

templates/capture-workflow.sh:54-59

Shell command substitution

RESULT=$(infsh app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

templates/capture-workflow.sh:86

Shell command substitution

RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION_ID --input '{}')

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

templates/capture-workflow.sh:105-107

Shell command substitution

RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

templates/capture-workflow.sh:114-115

Shell command substitution

RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

templates/capture-workflow.sh:1

Unix shell invocation

#!/bin/bash

This is an executable shell template that runs the browser automation CLI and handles user-supplied URLs or sessions. It is legitimate functionality, but it is real external command execution.

Medio

templates/form-automation.sh:30-32

Shell command substitution

RESULT=$(infsh app run agent-browser --function open --session new --input '{

The line captures output from the external browser automation CLI. This is intended behavior, but it can navigate sites, interact with pages, and capture page data.

Medio

templates/form-automation.sh:1

Unix shell invocation

#!/bin/bash

This is an executable shell template that runs the browser automation CLI and handles user-supplied URLs or sessions. It is legitimate functionality, but it is real external command execution.

Factores de riesgo

⚙️ Comandos externos (163)

🌐 Acceso a red (54)

📁 Acceso al sistema de archivos (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

Patrones detectados

Screen capture upload

Auditado por: codex Ver historial de auditorías →

Compartir y citar este informe

Comparte el informe de evaluación versionado, la insignia neutral, la tarjeta insertable y las citas. Skillstore presenta evidencias sin decidir si este Skill es seguro.

Abrir el informe versionado

Copiar enlace del informe

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

Insignia Markdown

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

Insignia HTML

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

Tarjeta para insertar

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

Citas académicas (APA · BibTeX · CFF)

Cita APA

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

Cita BibTeX

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

Comparar variantes

19 variantes instalables

Cada autor sigue siendo un skill instalable independiente. La variante recomendada se ordena según la evidencia de Skillstore.

Por qué esta variante es la primera

Mayor puntuación de Skillstore

Autor / fuente Puntuación de Skillstore Confianza de la evidencia Uso en Skillstore Actualizado

supercent-io Recomendado

supercent-io-agent-browser

Puntuación de Skillstore 78

Confianza de la evidencia Alto

Uso en Skillstore 37

Actualizado

2026-09-09

101-skills

101-skills-agent-browser

Puntuación de Skillstore 74

Confianza de la evidencia Medio

Uso en Skillstore 4

Actualizado

2026-09-09

vercel-labs

vercel-labs-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Alto

Uso en Skillstore 72

Actualizado

2026-09-09

qu-skills

qu-skills-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 42

Actualizado

2026-09-09

tul-sh

tul-sh-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 38

Actualizado

2026-09-09

am-will

am-will-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 37

Actualizado

2026-09-09

inference-sh-8

inference-sh-8-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 26

Actualizado

2026-09-09

skillssh

skillssh-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 18

Actualizado

2026-09-09

toolshell

toolshell-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 17

Actualizado

2026-09-09

inference-sh-9

inference-sh-9-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 16

Actualizado

2026-09-09

inferen-sh

inferen-sh-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 11

Actualizado

2026-09-09

inferencesh

inferencesh-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 11

Actualizado

2026-09-09

inference-sh-skills

inference-sh-skills-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 10

Actualizado

2026-09-09

inference-shell

inference-shell-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 10

Actualizado

2026-09-09

inference-sh-0

inference-sh-0-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 10

Actualizado

2026-09-09

infsh-skills

infsh-skills-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 9

Actualizado

2026-09-09

inf-sh

inf-sh-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 8

Actualizado

2026-09-09

inference-skills Actual

inference-skills-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 8

Actualizado

2026-09-09

halt-catch-fire

halt-catch-fire-agent-browser

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 4

Actualizado

2026-09-09

Puntuación de Skillstore

Por qué esta puntuación Confianza de la evidencia: Medio

Arquitectura

Mantenibilidad

Contenido

Comunidad

Cumplimiento de la especificación

Lo que puedes crear

Validar flujos del navegador

Ejecuta comprobaciones de formularios, inicio de sesión y navegación mientras recopilas capturas de pantalla o evidencia en video.

Capturar investigación web

Abre páginas públicas, extrae texto visible, recopila enlaces y guarda capturas de pantalla de páginas para revisión.

Automatizar tareas operativas

Repite flujos de trabajo autorizados del navegador en herramientas de administración después de confirmar los sitios de destino y las credenciales.

Prueba estos prompts

Abrir una página

Abre esta URL en una nueva sesión de navegador, muestra los elementos interactivos visibles y explica qué refs de elementos importan para el siguiente paso.

Rellenar un formulario

Navega a este formulario, identifica cada campo obligatorio, rellénalo con los datos de prueba proporcionados, envíalo y verifica la página de resultado.

Capturar evidencia

Graba el flujo de trabajo del navegador, realiza estos pasos, captura una captura de pantalla de página completa en el estado final y resume qué cambió.

Ejecutar un flujo de trabajo autenticado

Usa una sesión autenticada autorizada para completar este flujo de trabajo. Evita grabar campos sensibles, actualiza las refs después de la navegación y cierra la sesión cuando termines.

Mejores prácticas

Usa solo sitios, cuentas y credenciales autorizados para la automatización del navegador.
Actualiza los snapshots después de la navegación, el envío de formularios o los cambios dinámicos en la página.
Desactiva la grabación de video cuando puedan aparecer credenciales, tokens, datos personales o registros internos.

Evitar

No uses la rotación de proxy para eludir límites de tasa, controles de acceso o políticas del sitio.
No imprimas cookies, contraseñas, tokens ni datos de sesión en logs o artefactos capturados.
No subas archivos locales a menos que el sitio de destino, la ruta del archivo y el permiso sean explícitos.