皮亚杰建构写作法

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:42 PM UTC
• Version:
  1.0.1

Overview

This is a Markdown-only educational writing workflow with minor usability concerns but no code execution, data access, persistence, or deceptive behavior.

Safe to install from a security perspective. Expect it to steer suitable teaching or explanatory writing requests into a constructivist lesson format; enable it selectively if you do not want that style for general writing tasks, and avoid placing real student personal information in prompts unless you are comfortable processing it with the agent.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The trigger conditions are broad enough that the skill could activate on generic education or writing requests without strong scope boundaries. This can cause unintended invocation, steer the assistant into an inappropriate workflow, and reduce user control, though it does not by itself create code execution or data exfiltration risk.

Natural-Language Policy Violations

Medium

• Confidence: 72% confidence
• Finding: The skill metadata and body are written as Chinese-first and do not explicitly offer language selection, which can force outputs into an unintended language for some users. This is primarily a usability and policy-compliance issue that could confuse users or degrade task quality, but it does not materially increase classic security risk in this context.

VirusTotal

66/66 vendors flagged this skill as clean.