ClawHub
Back to skill

Security audit

🩹 Image Inpainting — Pro Pack on RunComfy

Security checks across malware telemetry and agentic risk

Overview

This is a coherent RunComfy image-inpainting skill that uses an external CLI and account token for its stated image-editing purpose.

Install only if you trust the RunComfy CLI and service. Use a dedicated or revocable RunComfy token where possible, be careful with private images or masks because they are processed by RunComfy, and confirm intent before using broad requests like object or watermark removal.

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
92% confidence
Finding
The trigger list includes broad, everyday phrases such as 'remove from image', 'remove object', 'patch the photo', and 'fill the hole', which can cause the skill to activate for ambiguous user requests that were not intended to invoke this specific tool. In an agent setting, overly broad activation increases the chance of unintended execution against user-supplied images or URLs, creating privacy, safety, and workflow-integrity risks even if the underlying CLI usage is otherwise constrained.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.