๐Ÿซง Image Edit โ€” Pro Pack on RunComfy

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only image-editing skill that clearly routes requested image edits through RunComfy, with expected third-party API and token use disclosed.

Install only if you trust RunComfy and the @runcomfy/cli package. Do not send sensitive private images or masks unless you are comfortable with RunComfy processing them, and confirm you have rights to edit images, especially for watermark, branding, or identity-preserving changes.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger condition is overly broad because it activates on generic phrases like "any explicit ask to edit an image," which can cause this skill to intercept requests that were intended for other tools or safer workflows. In a multi-skill agent, broad routing increases the chance of unintended third-party data transfer to RunComfy and execution of remote image-processing actions without sufficiently specific user intent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal