DingJi Course Design

• Outcome: Review
• Latest audit: May 29, 2026 at 9:32 PM UTC
• Version:
  1.0.0

Overview

This looks like a legitimate math course-design skill, but it stores learner profiles and sets reminders or notifications without clear consent, retention, or deletion controls.

Review before installing. Use it only if you are comfortable with persistent student progress profiles, scheduled reminders, external visualization or messaging tools, and file-transfer workflows; set explicit limits on stored learner data, notification recipients, tool use, and deletion of records.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (3)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The trigger text is broad enough to activate on ordinary educational requests like 'design math course' or 'create teaching plan', which can cause the skill to run unexpectedly. Over-broad activation increases the chance of unintended tool use, profiling, or external integrations being invoked without the user realizing this specific skill has been selected.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: This section describes persistent learner profiling, memory storage, and scheduled review/reminder behavior, but does not clearly warn users that their performance data may be retained over time and used to drive future notifications. In an educational context this is sensitive behavioral data, and silent persistence or reminders can violate user expectations and privacy requirements.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill references external or web-based tooling without warning that user content or learning data may leave the core chat environment. Even if the purpose is legitimate visualization or teaching support, undisclosed transmission to browser-based, API-based, or notification systems can expose student data and create privacy and compliance risks.

VirusTotal

65/65 vendors flagged this skill as clean.