Back to skill

Security audit

corrector-guiones-formula100k

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Spanish-language script-review skill with disclosed file handling, and no evidence of hidden persistence, credential use, exfiltration, or destructive behavior.

Install only if you want a Spanish neutral script-diagnosis workflow. Provide only scripts, transcripts, profile details, or document paths you intend the agent to read, and avoid handing it unrelated private files.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Line L082 mandates 'Español neutro, sin voseo argentino' and explicitly prohibits alternative forms, which is a language/locale restriction. The file does not offer the user any choice or opt-in for preferred dialect, so this is a natural-language policy violation under the locale rule.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

La skill instruye ejecutar textutil sobre una ruta proporcionada por el usuario para convertir archivos .docx, introduciendo una acción de sistema innecesaria para una skill principalmente textual. Aunque el comando es relativamente acotado y va entre comillas, sigue ampliando la superficie de ataque al promover acceso a archivos locales y ejecución de utilidades del host sobre entrada controlada por el usuario.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

El contenido instruccional del skill está redactado íntegramente en español y además da una instrucción operativa directa ('Lee este archivo completo antes de diagnosticar') sin ofrecer alternativa de idioma ni indicar que el skill sea explícitamente solo para usuarios hispanohablantes. Esto constituye una posible violación de política de idioma/locale al forzar un idioma específico sin opt-in del usuario.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document’s natural-language instructions, headings, and examples are fully in Spanish, which can impose a language choice on users. The policy allows fixed-language behavior only when the skill offers opt-in or clearly documents a justified locale restriction, neither of which appears here.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

En L014 se presenta la skill como 'solo texto', pero enseguida se documenta que debe leer archivos enviados por la usuaria y trabajar sobre audio mediante transcripción. Eso contradice la caracterización inicial de alcance, porque la skill no es estrictamente solo texto en su operación documentada.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.