ClawHub
Back to skill

Security audit

low-budget-3d

Security checks across malware telemetry and agentic risk

Overview

This skill is a prompt-writing style guide for low-budget Chinese 3D animation, with only minor usability and routing caveats.

Installers should expect this skill to steer image-prompt requests strongly toward a rough, low-budget Chinese 3D animation look. Review the trigger wording if precise routing matters, and explicitly request a non-English or bilingual final prompt if needed.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
The skill hard-requires the final prompt output to be in English, without considering the user's preferred language. This can override user intent and reduce usability, especially for users expecting Chinese-language outputs or bilingual assistance. In a prompt-generation skill, language coercion is a genuine policy/usability flaw because it can cause the agent to ignore user preferences or downstream system expectations.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The trigger term "rough CGI" is broader than the skill's stated niche of low-budget Chinese 3D / early-2000s Chinese animation aesthetics. Because it can describe many unrelated visual styles, it may cause unintended skill activation and misrouting of user requests, reducing precision and potentially overriding a better-matched skill.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.