🫧 GPT Image Edit — Pro Pack on RunComfy

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:43 PM UTC
• Version:
  0.1.4

Overview

This skill is a disclosed RunComfy wrapper for GPT Image 2 image editing, with no bundled executable code or hidden behavior found.

Install only if you trust RunComfy and are comfortable sending image URLs and edit prompts to its service. Protect `RUNCOMFY_TOKEN`, avoid private or sensitive images unless the service terms fit your needs, and choose output directories deliberately.

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 trigger definition includes the broad phrase "or any explicit ask to edit with this model," which is ambiguous and can cause the skill to activate outside narrowly scoped invocations. In an agent environment, overly broad routing increases the chance this skill is selected for loosely related image-edit requests, potentially sending user-provided image URLs and prompts to the external RunComfy service when a more appropriate or local tool should have been used.

VirusTotal

65/65 vendors flagged this skill as clean.