ClawHub
Back to skill

Security audit

NSFW Image Generation — Unrestricted AI Image Models

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed adult image-generation helper whose API key use, network calls, uploads, and downloads match its stated purpose.

Install only if you are comfortable with an adult-content image tool sending your prompts and selected images to Atlas Cloud and spending from your Atlas Cloud account. Use a dedicated low-balance API key, monitor usage, revoke the key when finished, and upload only images you are allowed and willing to send to that provider.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill requires access to environment variables and makes outbound network requests, but it does not declare corresponding permissions in a formal permission model. This creates a transparency and governance gap: users or platforms may not realize the skill can read a billing-linked API key and send prompts/images to a third-party service.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.