Algorithm Learning Platform Builder | 算法学习平台构建助手

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:37 PM UTC
• Version:
  1.0.1

Overview

This is a coherent educational skill for building interactive algorithm learning pages, with only normal disclosure caveats around broad routing and CDN-loaded demo libraries.

Installers should expect this skill to generate structured algorithm explanations and optional runnable HTML demos. Review generated HTML before publishing it, and replace CDN scripts with pinned local copies if offline use, strict privacy, or supply-chain control matters.

SkillSpector

By NVIDIA

Vulnerability Patterns

• System Prompt Leakage: Direct Leakage, Indirect Extraction, Tool-Based Exfiltration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (2)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill description is extremely broad and can be invoked for many generic planning, content-generation, or educational requests beyond a narrowly scoped algorithm-teaching use case. Overly broad routing increases the chance this skill is selected in unintended contexts, which can expose internal references, generate unnecessarily complex code/HTML, or bypass safer domain-specific skills.

Direct Prompt Extraction

High

• Category: System Prompt Leakage

Content

- `references/request-routing-rules.md`
- `references/output-quality-checklist.md`

# Output rules

## For planning requests
Output should include:

• Confidence: 83% confidence
• Finding: Output rules

VirusTotal

64/64 vendors flagged this skill as clean.