ClawHub
Back to skill

Security audit

Miaoji Model Shot Pro

Security checks across malware telemetry and agentic risk

Overview

This is a product photography planning skill with problematic race-specific casting language, but no hidden access, persistence, credential use, or unsafe automation.

Before installing, treat this as a planning aid and review any casting recommendations for advertising, marketplace, and anti-discrimination compliance. Prefer neutral criteria such as product fit, brand style, use case, age range where appropriate, and inclusive representation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The skill explicitly includes race-based model guidance (e.g., suggesting a 'white female') as a default strategic recommendation without user request, necessity, or policy justification. This can lead to discriminatory outputs, biased business decisions, and potential legal, platform-policy, or reputational harm, especially because the guidance is framed as an upgrade over a free version rather than as an optional, context-bound consideration.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal