Image Prompt Engineer

• Outcome: Pass
• Latest audit: Jun 9, 2026 at 2:59 PM UTC
• Version:
  1.0.2

Overview

This is a text-only image-prompt writing skill with no evidence of unsafe access, hidden actions, or persistence.

Install this if you want help producing paste-ready image prompts. Be aware it may activate for a range of image-prompt-related requests and will default to Midjourney when no model is specified; verify current model/version details for time-sensitive Midjourney work.

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: 88% confidence
• Finding: The skill description is broadly scoped and includes generic verbs like create, refine, translate, critique, and produce variants across many image-related tasks. In an agent routing system, this can cause over-triggering, where the skill activates for loosely related requests and may preempt more appropriate skills, increasing the chance of unintended prompt generation, policy bypass attempts, or mis-handling of adjacent content domains.

VirusTotal

64/64 vendors flagged this skill as clean.