Image Prompt Engineer

• Outcome: Pass
• Latest audit: May 29, 2026, 8:36 PM
• Version:
  1.0.1

Overview

This is a low-risk image prompt-writing guide with no executable code, credentials, or hidden system access.

Safe to install as an image-generation prompt helper. Consider narrowing its trigger wording if you only want it used for explicit AI image, Midjourney, DALL-E, Stable Diffusion, Flux, or photography prompt requests.

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 (1)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The manifest description includes broad trigger phrases such as 'write a prompt' and 'generate an image of', which can match many ordinary user requests and cause the skill to be invoked outside its narrow intended scope. Over-broad activation can lead to unnecessary prompt routing, capability confusion, and unintended influence over unrelated tasks, especially in agent systems that auto-select skills from descriptions.

VirusTotal

63/63 vendors flagged this skill as clean.