DingJi Long Image

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:36 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed math-course image generator that saves and uploads generated PNGs to provide download links.

Install only if you are comfortable with generated images being saved locally and uploaded to obtain a shareable download link. Avoid including private student information, confidential course material, or sensitive branding unless sharing that content through the platform upload flow is acceptable.

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)

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The README explicitly states that generated images are uploaded to cloud storage and a download link is returned, but it does not disclose where data is sent, what provider is used, or whether user-provided content may leave the local environment. This creates a real privacy and data-handling risk, especially if users include proprietary teaching material, student data, or branded content in the generated image.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger phrases are broad enough to match ordinary image-generation requests, which can cause the skill to activate outside its intended educational context. That increases the chance of unintended file creation and downstream upload behavior being invoked for users who did not explicitly ask for this specific skill.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill explicitly writes output files to a fixed outbound path and uploads them via a file-transfer tool, but it does not clearly disclose these data-handling actions to the user before execution. This is risky because generated content may include sensitive educational materials, names, or proprietary content, and automatic upload expands exposure beyond local generation.

VirusTotal

66/66 vendors flagged this skill as clean.