ClawHub
Back to skill

Security audit

Moodle Web Services Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Moodle administration helper that needs sensitive Moodle permissions, but those capabilities are disclosed, purpose-aligned, and not backed by hidden code or persistence.

Use this only with Moodle accounts authorized for the requested administrative tasks. Keep the Web Service token out of chat and version control, use the least-privilege token available, test changes in a staging course first, and require clear confirmation before modifying grades, enrollments, courses, or activities.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

El manifiesto indica usar la skill cuando el usuario pida crear cursos, inscribir usuarios, actualizar actividades o listar cursos/estudiantes, pero no define restricciones de contexto, frases exactas de activación ni ejemplos negativos. Esto puede solaparse con peticiones administrativas comunes y provocar invocaciones no deseadas fuera de un flujo claramente acotado a Moodle.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

Todo el contenido instructivo y descriptivo del archivo está redactado en español y no ofrece al usuario una opción de idioma ni documenta que la skill sea exclusivamente regional o para usuarios hispanohablantes. Según la política indicada, forzar un idioma sin opt-in puede constituir una violación de política lingüística.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.