ClawHub
Back to skill

Security audit

Prompt Quality Checklist

Security checks across malware telemetry and agentic risk

Overview

This is a text-only Chinese checklist for reviewing AI image/video prompts, with no code, installation commands, credential use, or privileged behavior.

This skill is reasonable to install if you want a Chinese-language checklist for reviewing AI storyboard prompts. Be aware that generic trigger words like “自查” or “检查清单” may invoke it outside the intended image/video prompt-review context, and avoid putting sensitive local asset paths into prompts that will be sent to external generation tools.

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
91% confidence
Finding
The trigger list includes broad terms like “检查清单”, “自查”, and “自审”, which can match many ordinary review or self-check requests unrelated to this narrowly scoped skill. Overbroad activation can cause the agent to invoke this skill in unintended contexts, overriding user intent or steering general conversations into rigid prompt-audit behavior.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.