Habilidades agent-browser
📦
agent-browser
Revisión del contenido r1 Crítico ⚙️ Comandos externos🌐 Acceso a red📁 Acceso al sistema de archivos
Automatiza tareas del navegador con agentes de IA
Las tareas web suelen requerir navegación repetida, entrada de formularios y comprobaciones visuales. Esta habilidad proporciona a Claude, Codex y Claude Code un flujo de trabajo estructurado en el navegador mediante inference.sh.
Compatible con: Claude Codex Code(CC)
No instales este Skill automáticamente.
La política canónica exige la revisión de un operador antes de cualquier acción de instalación.
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-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.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.
Pruébalo
Usando "agent-browser". Inspeccionar una página de precios y capturar llamadas a la acción visibles.
Resultado esperado:
- Se abrió la página y se encontró el selector principal de planes, el conmutador de facturación y el botón de contacto con ventas.
- Se capturó una captura de pantalla del viewport y se señaló que el plan empresarial requiere un flujo de contacto separado.
- No se envió ningún formulario y no se accedió a contenido autenticado.
Usando "agent-browser". Rellenar un formulario de contacto de prueba con datos de muestra aprobados.
Resultado esperado:
- Se identificaron los controles de nombre, email, mensaje y envío a partir de la snapshot actual.
- Se rellenaron los valores de prueba aprobados y se envió el formulario.
- El mensaje de confirmación apareció después del envío y se cerró la sesión.
Usando "agent-browser". Grabar un flujo de trabajo corto para una revisión de documentación.
Resultado esperado:
- Se inició la grabación antes del flujo de trabajo aprobado y se detuvo cuando se cerró la sesión.
- Se capturaron capturas de pantalla clave durante los pasos de navegación.
- Se marcó un paso para revisión manual porque el botón esperado no estaba visible.
Auditoría de seguridad
Críticov4 • 5/7/2026 Abrir el informe versionado
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.
9
Archivos escaneados
2,105
Líneas analizadas
84
Elementos de revisión
0
Falsos positivos ignorados
Preocupaciones de seguridad confirmadas (6)
Crítico
Pipe to shell pattern
curl -fsSL https://cli.inference.sh | sh && infsh login
The quick start pipes a remote installer from cli.inference.sh directly into sh. This can execute unverified network content on the user machine.
Alto
Screen capture upload
description: "Browser automation for AI agents via inference.sh. Navigate web pages, interact with e
The skill description advertises screenshots and video recording for browser sessions. Captures can include credentials or private page content and may be returned through the external service.
Alto
Cookie Extraction Guidance
The authentication reference shows extracting browser cookies and printing them after an authenticated session. This can expose session tokens or private account data outside the browser.
The section title and examples directly describe cookie extraction from an authenticated browser session. The risk is clear even though the code is presented as documentation.
Alto
Rate Limit Evasion via Proxy Rotation
The proxy guide includes a rate-limit avoidance workflow that rotates proxies for scraping. This supports evasion of site controls and can enable abusive automation.
The heading and example explicitly connect proxy rotation with rate-limit avoidance. This is strong intent-level evidence beyond generic proxy support.
Alto
Local File Upload Capability
The skill supports uploading local file paths into browser file inputs. Without explicit user review, an agent could disclose local files to an external website.
The documented upload action accepts file paths and sends them through a browser form. The capability is legitimate but has a clear data disclosure risk.
Medio
Arbitrary Page JavaScript Execution
The skill exposes an execute function for running custom JavaScript in the current page. This can extract page data or alter page state during authenticated sessions.
The function is documented as accepting custom JavaScript code. The browser context makes the risk concrete, but it is also an intended automation feature.
Elementos de revisión de capacidades (84)
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
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION --input '{
The authentication guide shows extracting and printing cookie-related browser data from an authenticated session. That can expose session secrets outside the browser context.
Alto
Shell command substitution
COOKIES=$(echo $RESULT | jq -r '.result')
The authentication guide shows extracting and printing cookie-related browser data from an authenticated session. That can expose session secrets outside the browser context.
Alto
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION --input '{
The authentication guide shows extracting and printing cookie-related browser data from an authenticated session. That can expose session secrets outside the browser context.
Alto
SOCKS proxy
"proxy_url": "socks5://privacy-proxy.example.com:1080"
The proxy documentation explicitly supports SOCKS proxy routing. This can hide traffic origin and is paired with scraping and anonymity workflows in the same reference.
Alto
SOCKS proxy
### SOCKS5 Proxy
The proxy documentation explicitly supports SOCKS proxy routing. This can hide traffic origin and is paired with scraping and anonymity workflows in the same reference.
Alto
SOCKS proxy
{"proxy_url": "socks5://proxy.example.com:1080"}
The proxy documentation explicitly supports SOCKS proxy routing. This can hide traffic origin and is paired with scraping and anonymity workflows in the same reference.
Alto
Hardcoded URL
curl -fsSL https://cli.inference.sh | sh && infsh login
The URL is used to download the CLI installer that is piped into a shell. This is a real network trust and code execution risk.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
URL=$(echo $RESULT | jq -r '.url')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
URL=$(echo $RESULT | jq -r '.url')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
ELEMENTS=$(echo $RESULT | jq -r '.elements_text')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
TOTP_CODE=$(oathtool --totp -b "$TOTP_SECRET")
The example invokes oathtool with a TOTP secret during automated login. This is legitimate but processes authentication secrets through shell commands.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
SESSION=$(login)
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
export PASSWORD=$(cat /path/to/secure/password)
The example reads passwords from local files or a secrets manager into shell environment variables. This is legitimate guidance but still handles sensitive credentials in shell state.
Medio
Shell command substitution
export PASSWORD=$(vault read -field=password secret/app)
The example reads passwords from local files or a secrets manager into shell environment variables. This is legitimate guidance but still handles sensitive credentials in shell state.
Medio
Shell command substitution
URL=$(echo $RESULT | jq -r '.url')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
ELEMENTS=$(echo $RESULT | jq -r '.elements_text')
The finding is a shell command substitution in skill-provided instructions. Legitimate use is possible, but the pattern executes commands and is kept fail-closed.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION --input '{}')
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
echo "IP via proxy: $(echo $RESULT | jq -r '.result')"
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
SESSION_ID=$(echo $SESSION | jq -r '.session_id')
The proxy reference includes executable shell examples that run infsh through proxy settings. This is intended functionality, but it enables external network automation through a shell workflow.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function interact --session $SESSION --input '{
The documentation shows command substitution around infsh interaction examples. It is intended usage but still executes an external browser automation CLI.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function interact --session $SESSION --input '{
The documentation shows command substitution around infsh interaction examples. It is intended usage but still executes an external browser automation CLI.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
VIDEO=$(echo $RESULT | jq -r '.video')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function interact --session $SESSION --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
SUCCESS=$(echo $RESULT | jq -r '.success')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
echo "Message: $(echo $RESULT | jq -r '.message')"
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
echo "Debug video: $(echo $CLOSE_RESULT | jq -r '.video')"
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
echo "Documentation video: $(echo $RESULT | jq -r '.video')"
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
VIDEO=$(echo $CLOSE_RESULT | jq -r '.video')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
TASK_ID=$(date +%Y%m%d-%H%M%S)
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
VIDEO=$(echo $RESULT | jq -r '.video')
The video reference includes executable shell examples that start browser sessions and collect recording output. These workflows can capture sensitive page activity if run on private sessions.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
Medio
Shell command substitution
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
Medio
Shell command substitution
SESSION=$(infsh app run agent-browser --function open --session new --input '{
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function close --session $SESSION --input '{}')
The main skill instructions include executable Bash examples using command substitution with infsh. This is intended usage but still asks agents or users to run external commands.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Unix shell invocation
#!/bin/bash
This is an executable Bash template shipped with the skill. The script invokes the infsh browser automation CLI and can act on user-provided web targets.
Medio
Shell command substitution
CLOSE_RESULT=$(infsh app run agent-browser --function close --session $SESSION_ID --input '{}' 2>/de
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
VIDEO=$(echo $CLOSE_RESULT | jq -r '.video // empty')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
URL=$(echo $RESULT | jq -r '.url')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
TITLE=$(echo $RESULT | jq -r '.title')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function snapshot --session $SESSION_ID --input '{}')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function execute --session $SESSION_ID --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Unix shell invocation
#!/bin/bash
This is an executable Bash template shipped with the skill. The script invokes the infsh browser automation CLI and can act on user-provided web targets.
Medio
Shell command substitution
RESULT=$(infsh app run agent-browser --function open --session new --input '{
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Shell command substitution
SESSION_ID=$(echo $RESULT | jq -r '.session_id')
This is active template code that runs infsh or parses its output through shell command substitution. The template can browse user-supplied URLs through a network-backed CLI.
Medio
Unix shell invocation
#!/bin/bash
This is an executable Bash template shipped with the skill. The script invokes the infsh browser automation CLI and can act on user-provided web targets.
Bajo
Hardcoded URL
references/authentication.md:24-26 references/authentication.md:51 references/authentication.md:52 references/authentication.md:70-72 references/authentication.md:80 references/authentication.md:97 references/authentication.md:115 references/authentication.md:116 references/authentication.md:128 references/authentication.md:129 references/authentication.md:133 references/authentication.md:153-156 references/authentication.md:179-181 references/authentication.md:202 references/authentication.md:215-217 references/authentication.md:218 references/authentication.md:222-223 references/authentication.md:243 references/authentication.md:246 references/authentication.md:285 references/authentication.md:292 references/authentication.md:21 references/authentication.md:68 references/authentication.md:174 references/proxy-support.md:22-25 references/proxy-support.md:35-40 references/proxy-support.md:65-68 references/proxy-support.md:76 references/proxy-support.md:107 references/proxy-support.md:111 references/proxy-support.md:113-116 references/proxy-support.md:119-121 references/proxy-support.md:137-142 references/proxy-support.md:150-153 references/proxy-support.md:186-189 references/proxy-support.md:192-194 references/proxy-support.md:195 references/proxy-support.md:267-270 references/proxy-support.md:273 references/proxy-support.md:294 references/proxy-support.md:50 references/proxy-support.md:90 references/snapshot-refs.md:124-126 references/snapshot-refs.md:136-138 references/snapshot-refs.md:140 references/snapshot-refs.md:142 references/video-recording.md:23-26 references/video-recording.md:38 references/video-recording.md:39 references/video-recording.md:48-52 references/video-recording.md:87-90 references/video-recording.md:93-95 references/video-recording.md:97 references/video-recording.md:100 references/video-recording.md:103 references/video-recording.md:104 references/video-recording.md:119-124 references/video-recording.md:156 references/video-recording.md:157 references/video-recording.md:168-171 references/video-recording.md:178 references/video-recording.md:179 references/video-recording.md:195 references/video-recording.md:197-200 references/video-recording.md:206 references/video-recording.md:207 references/video-recording.md:84 references/video-recording.md:116 references/video-recording.md:163 references/video-recording.md:192 SKILL.md:9 SKILL.md:15-21 SKILL.md:21-27 SKILL.md:27-32 SKILL.md:32-56 SKILL.md:56-62 SKILL.md:62-63 SKILL.md:63 SKILL.md:64 SKILL.md:65-66 SKILL.md:66-67 SKILL.md:67-73 SKILL.md:73 SKILL.md:74 SKILL.md:75 SKILL.md:76 SKILL.md:77 SKILL.md:78 SKILL.md:79 SKILL.md:80 SKILL.md:81 SKILL.md:82 SKILL.md:83 SKILL.md:84 SKILL.md:85-86 SKILL.md:86 SKILL.md:87 SKILL.md:91-93 SKILL.md:93-99 SKILL.md:99-112 SKILL.md:112-125 SKILL.md:125-131 SKILL.md:131-137 SKILL.md:137-145 SKILL.md:145-152 SKILL.md:152-158 SKILL.md:158-164 SKILL.md:164-170 SKILL.md:170-176 SKILL.md:176-182 SKILL.md:182-187 SKILL.md:187-212 SKILL.md:212-226 SKILL.md:226-230 SKILL.md:230-241 SKILL.md:241-245 SKILL.md:245-259 SKILL.md:259-265 SKILL.md:265-266 SKILL.md:266-271 SKILL.md:271-277 SKILL.md:34-36 SKILL.md:37 SKILL.md:114-118 SKILL.md:213-215 SKILL.md:231-233 SKILL.md:246-249 SKILL.md:257 SKILL.md:32-56 SKILL.md:112-125 SKILL.md:212-226 SKILL.md:230-241 SKILL.md:245-259 templates/authenticated-session.sh:40-42 templates/authenticated-session.sh:43 templates/authenticated-session.sh:70-73 templates/authenticated-session.sh:74 templates/authenticated-session.sh:97 templates/authenticated-session.sh:98 templates/authenticated-session.sh:127-128 templates/authenticated-session.sh:130 templates/authenticated-session.sh:1 templates/capture-workflow.sh:28 templates/capture-workflow.sh:31 templates/capture-workflow.sh:54-59 templates/capture-workflow.sh:60 templates/capture-workflow.sh:63 templates/capture-workflow.sh:64 templates/capture-workflow.sh:86 templates/capture-workflow.sh:105-107 templates/capture-workflow.sh:114-115 templates/capture-workflow.sh:126-127 templates/capture-workflow.sh:132-133 templates/capture-workflow.sh:138-139 templates/capture-workflow.sh:1 templates/form-automation.sh:30-32 templates/form-automation.sh:33 templates/form-automation.sh:102 templates/form-automation.sh:104 templates/form-automation.sh:105 templates/form-automation.sh:110 templates/form-automation.sh:1
🌐 Acceso a red (54)
references/authentication.md:25 references/authentication.md:71 references/authentication.md:154 references/authentication.md:180 references/authentication.md:194 references/commands.md:25 references/commands.md:56 references/proxy-support.md:23 references/proxy-support.md:24 references/proxy-support.md:36 references/proxy-support.md:37 references/proxy-support.md:54 references/proxy-support.md:55 references/proxy-support.md:56 references/proxy-support.md:66 references/proxy-support.md:94 references/proxy-support.md:95 references/proxy-support.md:96 references/proxy-support.md:100 references/proxy-support.md:101 references/proxy-support.md:102 references/proxy-support.md:138 references/proxy-support.md:139 references/proxy-support.md:151 references/proxy-support.md:161 references/proxy-support.md:162 references/proxy-support.md:175 references/proxy-support.md:187 references/proxy-support.md:188 references/proxy-support.md:252 references/proxy-support.md:259 references/proxy-support.md:152 references/proxy-support.md:165 references/proxy-support.md:168 references/video-recording.md:24 references/video-recording.md:49 references/video-recording.md:88 references/video-recording.md:120 references/video-recording.md:198 SKILL.md:9 SKILL.md:11 SKILL.md:17 SKILL.md:20 SKILL.md:35 SKILL.md:115 SKILL.md:133 SKILL.md:147 SKILL.md:148 SKILL.md:214 SKILL.md:232 SKILL.md:247 SKILL.md:281 SKILL.md:282 templates/authenticated-session.sh:118
📁 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 uploadPipe to shell pattern
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.
Copiar enlace del informe
https://skillstore.io/skills/inference-sh-0-agent-browser/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportInsignia Markdown
[](https://skillstore.io/skills/inference-sh-0-agent-browser?utm_source=security_passport_badge)Insignia HTML
<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>Tarjeta para insertar
<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>Citas académicas (APA · BibTeX · CFF)
Cita APA
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/4Cita BibTeX
@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}
}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-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"
Comparar variantes
19 variantes instalablesCada 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 52
Actualizado
2026-09-09
101-skills-agent-browser
Puntuación de Skillstore 74
Confianza de la evidencia Medio
Uso en Skillstore 10
Actualizado
2026-10-12
vercel-labs-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Alto
Uso en Skillstore 91
Actualizado
2026-09-09
qu-skills-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 46
Actualizado
2026-09-09
tul-sh-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 44
Actualizado
2026-09-09
am-will-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 43
Actualizado
2026-10-23
inference-sh-8-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 32
Actualizado
2026-09-09
skillssh-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 23
Actualizado
2026-09-09
toolshell-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 22
Actualizado
2026-09-09
inference-sh-9-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 21
Actualizado
2026-09-09
infsh-skills-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 18
Actualizado
2026-09-09
inferen-sh-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 17
Actualizado
2026-09-09
inference-sh-skills-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 16
Actualizado
2026-09-09
inferencesh-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 16
Actualizado
2026-09-09
inference-sh-0 Actual
inference-sh-0-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 16
Actualizado
2026-09-09
inference-shell-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 15
Actualizado
2026-09-09
inf-sh-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 14
Actualizado
2026-09-09
inference-skills-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 14
Actualizado
2026-09-09
halt-catch-fire-agent-browser
Puntuación de Skillstore 38
Confianza de la evidencia Medio
Uso en Skillstore 8
Actualizado
2026-09-09
Puntuación de Skillstore
Por qué esta puntuación Confianza de la evidencia: Medio 45
Arquitectura
85
Mantenibilidad
87
Contenido
70
Comunidad
83
Cumplimiento de la especificación
Lo que puedes crear
Comprobar flujos de trabajo web
Ejecuta acciones de navegador repetibles, captura pantallas y verifica los resultados visibles después de cada paso.
Recopilar evidencia de páginas
Abre páginas públicas, extrae texto y enlaces visibles, y guarda capturas de pantalla para revisión.
Automatizar tareas administrativas
Navega por herramientas autenticadas, rellena formularios y registra flujos de trabajo seleccionados después de una aprobación explícita.
Prueba estos prompts
Abrir y resumir una página
Abre esta URL con agent-browser, captura el estado visible de la página y resume los principales elementos interactivos: [URL]
Rellenar un formulario simple
Usa agent-browser para inspeccionar este formulario, identificar las refs @e necesarias, rellenar los valores aprobados, enviarlo e informar el resultado: [URL]
Capturar evidencia para un flujo de trabajo
Ejecuta este flujo de trabajo de navegador aprobado, toma capturas de pantalla después de los pasos clave y explica cualquier acción fallida sin reintentar pasos destructivos: [WORKFLOW]
Auditar una sesión autenticada
Después de que confirme el objetivo y las credenciales, usa agent-browser para realizar las comprobaciones autenticadas aprobadas, evita registrar secretos y cierra la sesión al terminar.
Mejores prácticas
- Confirma la URL de destino, la sensibilidad de los datos y las acciones permitidas antes de abrir una sesión de navegador.
- Vuelve a crear una snapshot después de la navegación o de actualizaciones dinámicas de la página para que cada acción use refs @e actuales.
- Desactiva la grabación de video al manejar credenciales, datos privados o contenido regulado.
Evitar
- No ejecutes el instalador remoto mediante una pipe hacia shell sin verificación.
- No uses la rotación de proxies para eludir límites de tasa, controles de acceso o políticas del sitio.
- No extraigas cookies, cargues archivos locales ni ejecutes JavaScript de página sin aprobación explícita.
Preguntas frecuentes
¿Esta habilidad requiere otro servicio?
Sí. Requiere la CLI de inference.sh y una cuenta infsh autenticada.
¿Puede interactuar con páginas con sesión iniciada?
Sí, pero las credenciales y los datos de sesión necesitan aprobación explícita del usuario y un manejo cuidadoso.
¿Qué son las refs @e?
Son referencias compactas de elementos devueltas por snapshots para que los agentes puedan hacer clic, rellenar y seleccionar controles de página.
¿Puede grabar video?
Sí. La grabación es opcional y debe permanecer desactivada en sesiones sensibles.
¿Admite proxies?
Sí. El soporte de proxy está documentado para pruebas y acceso corporativo, pero el uso indebido puede infringir las políticas del sitio.
¿Es segura para sitios web arbitrarios?
Usa precaución. La automatización del navegador puede activar acciones reales, exponer datos de página o cargar archivos si se usa indebidamente.
Detalles del desarrollador
Autor
inference-sh-0Licencia
MIT
Revisión de Skillstore
r1
Aviso de versión
El autor no declaró una versión.
Ref.
a25199bc7d6b82598536822d1738eb5d5f54025b
Actualidad del mantenimiento
18/7/2026
Uso
8 descargas · 190 vistas
Estructura de archivos