AI Prompt Generator

• Outcome: Pass
• Latest audit: May 28, 2026, 8:23 AM
• Version:
  1.0.0

Overview

This is a local prompt-generation helper with no evidence of credential access, network activity, persistence, or destructive behavior.

Safe for normal use as a local prompt generator. Before installing, be aware that it may be selected for a wide range of prompt-writing tasks and that generated prompts often default to Chinese phrasing; review outputs before using them with other AI systems, especially for high-stakes topics.

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: 93% confidence
• Finding: The skill description activates on extremely broad conditions such as 'any AI prompt engineering needs,' which can cause the agent to invoke this skill for many loosely related requests. Over-broad routing increases the chance of misapplication, prompt-scope hijacking, and unintended interception of user tasks that should be handled by a narrower or safer skill.

Natural-Language Policy Violations

Medium

• Confidence: 84% confidence
• Finding: The skill heavily centers Chinese-language examples and command arguments without stating that outputs are language-agnostic or user-selectable. This can bias agent behavior toward Chinese prompts even when the user did not request that language, reducing reliability and potentially causing incorrect or undesired outputs.

VirusTotal

66/66 vendors flagged this skill as clean.