ClawHub
Back to skill

Security audit

Ai Industry Infographic

Security checks across malware telemetry and agentic risk

Overview

This skill is a documented workflow for creating AI-industry infographic prompt packages, with no hidden install code or credential-seeking behavior found.

Install this if you want a rigorous AI-industry infographic research workflow. Be aware that its activation triggers are somewhat broad, so users should invoke it only for AI-industry infographic packages rather than ordinary prompt-writing requests.

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
92% confidence
Finding
The trigger list includes broad phrases such as '生成Prompt' and '做个选题的生图包' that can match many ordinary user requests outside this skill’s narrow intended scope. Over-broad activation can cause the agent to invoke this skill in inappropriate contexts, leading to prompt hijacking of workflow selection, irrelevant web-research behavior, or generation of productized output when the user only asked for lightweight help.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.