AI Prompt 工具箱

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:30 PM UTC
• Version:
  1.0.1

Overview

This appears to be a prompt-template helper with broad routing language, but no evidence of hidden execution, data access, persistence, or destructive behavior.

Install only if you want a broad prompt-template assistant. Be aware it may activate for many ordinary tasks, so review whether its routing language is acceptable for your workspace; no evidence here suggests it runs code, accesses credentials, or persists data.

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: 92% confidence
• Finding: The skill instructs users to describe nearly any need and promises to recommend or fill a prompt template across writing, coding, analysis, translation, and business tasks. This broad activation scope can cause the platform to invoke the skill for many ordinary requests, increasing prompt-surface exposure and making it easier for unrelated or sensitive user inputs to be routed through the skill unexpectedly.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The manifest description advertises extremely broad coverage of common user activities without specifying precise invocation conditions. In a skill-routing environment, this can make the skill match a wide range of everyday requests and overshadow more appropriate specialized skills, creating unnecessary exposure to prompt injection, misrouting, or unintended handling of user data.

VirusTotal

64/64 vendors flagged this skill as clean.