Skills para agentes de IA

security-review · GitHub

Revisión de seguridad

Rastrea límites de confianza y flujos de datos de riesgo a través del código.

Instrucciones originales de la skill

La plantilla técnica se mantiene en inglés para usarla directamente con los agentes compatibles. La explicación, selección y comprobaciones están localizadas.

Instalación

gh skills install github/awesome-copilot security-review

GitHub CLI

Ideal para

  • Pre-merge security review
  • Auth and permission changes
  • Input, secret, and data-flow analysis

Qué cambia esta skill

  • Reasons across components and follows untrusted input toward sensitive operations.
  • Looks for authorization, secret handling, injection, and unsafe boundary assumptions.
  • Produces review findings that can be checked against the actual implementation.

Flujo recomendado

  • Map entry points, trust boundaries, sensitive data, and privileged operations.
  • Trace realistic attacker-controlled inputs through the implementation.
  • Rank findings by evidence and impact, then recommend testable remediations.

Qué revisar antes de confiar

  • An agent review is not a substitute for threat modeling or professional assessment.
  • Validate every finding; both false positives and missed vulnerabilities are possible.
  • Do not expose secrets, production data, or private code to an unauthorized model.

Fuente y mantenimiento

GitHub · awesome-copilot