ClawHub
Back to skill

Security audit

AIGC佬猫剧本转提示词

Security checks across malware telemetry and agentic risk

Overview

This is a text-only skill for turning user-provided scripts into AI storyboard prompts, with no executable behavior or privileged access.

Install only if you want a Chinese-language script-to-storyboard prompt workflow. Be aware it may activate for broad script or AI-prompt requests, so check that it is being used only for screenplay/storyboard conversion, and avoid feeding scripts you do not have rights or permission to process.

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 activation condition is broad enough to trigger on common requests involving scripts, storyboards, animation prompts, or AI prompt generation, which can cause the skill to over-activate outside a tightly defined scope. Over-broad routing increases the chance of prompt hijacking of unrelated tasks, accidental interception of sensitive user content, or unsafe transformation of content that should have been handled by a narrower or policy-aware skill.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.