Pilot Ai Tutoring System Setup

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.0.0

Overview

This skill is for creating an educational progress-tracking subagent, but it asks users to approve broad OpenClaw device permissions that are not clearly limited to that purpose.

Review this carefully before installing. Only approve a specific, understood permission request, not a generic latest request, and avoid granting admin, pairing, approvals, or secrets access unless you can justify each permission. Do not use real student identifiers or sensitive education records unless you have consent and a clear retention/deletion plan.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The skill explicitly routes learner responses, progress, grades, and assessment history between multiple agents, but the description does not warn users that educational performance data is being transmitted and retained. This creates a real privacy and informed-consent issue because operators may deploy it without understanding the sensitivity and persistence of student data.

VirusTotal

64/64 vendors flagged this skill as clean.