Historial de auditorías
skill-installer - 6 auditorías
Versión de auditoría 6
Más reciente Riesgo bajoJan 21, 2026, 07:36 PM
This skill provides legitimate package management functionality for installing Codex skills from GitHub repositories. The static analyzer detected numerous false positives from JSON content. Network access and filesystem operations are appropriate for a skill installer. The skill references helper scripts that are not present in the directory, which may cause runtime errors but does not pose a security threat.
Problemas de riesgo bajo (2)
Factores de riesgo
🌐 Acceso a red (5)
⚙️ Comandos externos (16)
📁 Acceso al sistema de archivos (5)
🔑 Variables de entorno (2)
Versión de auditoría 5
Riesgo medioJan 17, 2026, 02:38 AM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Factores de riesgo
🌐 Acceso a red (5)
🔑 Variables de entorno (4)
⚙️ Comandos externos (16)
📁 Acceso al sistema de archivos (5)
Patrones detectados
Versión de auditoría 4
Riesgo medioJan 17, 2026, 02:38 AM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Factores de riesgo
🌐 Acceso a red (5)
🔑 Variables de entorno (4)
⚙️ Comandos externos (16)
📁 Acceso al sistema de archivos (5)
Patrones detectados
Versión de auditoría 3
SeguroJan 7, 2026, 01:32 AM
Pure prompt-based skill containing only documentation and AI behavior instructions. No executable code, scripts, or network calls are included in this skill. The referenced helper scripts are external dependencies that Codex would execute, not part of this skill package.
Versión de auditoría 2
SeguroJan 7, 2026, 01:32 AM
Pure prompt-based skill containing only documentation and AI behavior instructions. No executable code, scripts, or network calls are included in this skill. The referenced helper scripts are external dependencies that Codex would execute, not part of this skill package.
Versión de auditoría 1
SeguroJan 7, 2026, 01:32 AM
Pure prompt-based skill containing only documentation and AI behavior instructions. No executable code, scripts, or network calls are included in this skill. The referenced helper scripts are external dependencies that Codex would execute, not part of this skill package.