Habilidades provider-management Historial de auditorías
📦

Historial de auditorías

provider-management - 6 auditorías

Versión de auditoría 6

Más reciente Riesgo medio

Jun 28, 2026, 12:25 PM

Static analysis reported many external command hits, but review shows these are Markdown inline code spans and fenced examples rather than executable scripts. The real risks are semantic: the skill documents command-line handling of API keys and session tokens, and it stores credentials and OAuth tokens under a hidden home-directory path without verifiable encryption.

1
Archivos escaneados
218
Líneas analizadas
7
hallazgos
codex
Auditado por
Problemas de riesgo medio (2)
Sensitive Provider Credentials Are Entered Through Commands
The documented setup flow passes API keys and subscription session tokens through slash-command arguments. This can expose secrets in chat transcripts, logs, command history, telemetry, or shared screenshots depending on the host environment.
Local Credential And OAuth Token Storage Requires Stronger Guarantees
The skill documents auth.json and tokens.json under a hidden home-directory path and mentions file permissions, but no implementation is present to verify encryption, permission enforcement, token rotation, or safe deletion.
Problemas de riesgo bajo (3)
Static External Command Findings Are Markdown Examples
The repeated Ruby or shell backtick detections come from Markdown inline code spans and fenced bash examples for provider commands, model names, and provider IDs. No standalone script, shell invocation, or dynamic command construction is present in the scanned file.
Weak Cryptography Detections Are Token And Model Text Matches
The weak cryptography blocker detections are not supported by evidence in the file. The flagged areas contain metadata, auth labels, model names, or credential examples, and no MD5, SHA1, DES, RC4, or custom cryptographic implementation appears in SKILL.md.
System Reconnaissance Detection Is Troubleshooting Guidance
The system reconnaissance hit is tied to a troubleshooting sentence about ensuring a session token is valid. No host enumeration, environment discovery, or system information collection is described at the cited location.

Patrones detectados

Command-Line Secret HandlingPersistent Token Storage

Versión de auditoría 3

Seguro

Jan 10, 2026, 10:41 AM

Pure documentation-only skill. No code execution, no file system access, no network calls. SKILL.md contains only command documentation for a provider management system.

1
Archivos escaneados
218
Líneas analizadas
0
hallazgos
claude
Auditado por
No se encontraron problemas de seguridad

Versión de auditoría 2

Seguro

Jan 10, 2026, 10:41 AM

Pure documentation-only skill. No code execution, no file system access, no network calls. SKILL.md contains only command documentation for a provider management system.

1
Archivos escaneados
218
Líneas analizadas
0
hallazgos
claude
Auditado por
No se encontraron problemas de seguridad

Versión de auditoría 1

Seguro

Jan 10, 2026, 10:41 AM

Pure documentation-only skill. No code execution, no file system access, no network calls. SKILL.md contains only command documentation for a provider management system.

1
Archivos escaneados
218
Líneas analizadas
0
hallazgos
claude
Auditado por
No se encontraron problemas de seguridad