ClawHub
Back to skill

Security audit

IP 形象资产Ip Character Image System

Security checks across malware telemetry and agentic risk

Overview

This skill is a prompt-writing workflow for IP character image assets and does not request privileged system access or hidden execution.

Install this if you want a structured prompt system for character/IP image asset production. Users should still review generated prompts for brand or copyright-sensitive style references, but the skill itself is text-only and does not show hidden system access or privileged behavior.

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
87% confidence
Finding
The default prompt auto-invokes the skill through a broad activation phrase without any embedded constraints on when it should be used. This can cause overbroad or unintended routing to the skill, especially when user input only loosely matches the domain, increasing the chance of inappropriate invocation or prompt-scope confusion rather than direct code-execution risk.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.