Star200+

Evaluaci贸n previa a la instalaci贸n

Browser Use Informe de evaluaci贸n.

Una decisi贸n de instalaci贸n legible por m谩quina para Agents: afinidad con la tarea, Trust Score, Audit Score, seguridad de instalaci贸n, superficie de permisos y un plan de validaci贸n concreto antes de tocar el espacio de trabajo.

AprobadoRiesgo bajoPermitir Pol铆tica
90
Informe de evaluaci贸n
89
Confianza
92
Auditor铆a
84
Seguridad de Agent

Preselecci贸n

All required eval gates passed for an agent shortlist.

Controles obligatorios

Comprobaciones que un Agent debe superar antes de instalar

Abrir JSON

Ajuste de tarea

84

Aprobado

Task wording matches this skill metadata.

  • Evaluate Browser Use before installing it in an agent workflow
  • agent-frameworks
  • Browser automation workflows; Claude Code teams; teams that value GitHub adoption signals

Ruta de instalaci贸n

92

Aprobado

Install handoff is available.

  • npx skills add browser-use/browser-use

Seguridad del comando de instalaci贸n

92

Aprobado

Ruta est谩ndar de paquete o instalaci贸n en tiempo de ejecuci贸n

  • npx skills add browser-use/browser-use

Puntuaci贸n de confianza

89

Aprobado

Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.

  • Candidata de producci贸n
  • 99K estrellas de GitHub
  • MIT

Puntuaci贸n de auditor铆a

92

Aprobado

Seguro para probar

  • No major audit warning from metadata.

Control de seguridad de Agent

84

Aprobado

Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

  • Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.
  • Verified listing

Claridad de licencia

86

Aprobado

MIT

  • MIT

Superficie de permisos

86

Aprobado

network or browser access

  • Browser automation: medium
  • Network access: medium

Plan de validaci贸n

Qu茅 debe hacer el Agent despu茅s

  1. 1Inspect repository, README/SKILL.md, license, and recent commits before production use.
  2. 2Install in an isolated workspace or sandbox with no production secrets available.
  3. 3Run the smallest representative task and record files touched, commands run, network access, and outputs.
  4. 4Compare the selected skill against at least one alternative when the eval status is review or failed.
  5. 5Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

No usar cuando

Condiciones que requieren otra skill

  • Equipos que necesitan un SLA con soporte del proveedor
  • Entornos de alta conformidad sin revisi贸n interna de seguridad
  • No major risk signals from current metadata
  • No major trust warnings detected from available metadata
  • Production credentials, payments, or irreversible account changes without explicit human review
  • Sensitive private data before reviewing repository code, license, and permission surface

Comprobaciones de apoyo

Se帽ales de confianza detr谩s de la decisi贸n

Completitud de README/SKILL.md

Advertencia

74

Los metadatos p煤blicos necesitan m谩s contexto de README/SKILL.md

Mantenimiento reciente

Aprobado

88

2 meses desde el 煤ltimo push

Alternativas disponibles

Aprobado

82

Alternative skills are available for comparison.