ClawHub
Back to skill

Security audit

business-ai-expert

Security checks across malware telemetry and agentic risk

Overview

This is a consulting-oriented business AI skill with no executable code, persistence, credential access, or hidden system changes.

Before installing, consider whether you want business AI advice that often includes Chinese-market platforms and regulatory context; users outside that context should explicitly state their target market.

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 (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger description is broad enough to match generic business or AI-adjacent requests, which can cause the skill to activate outside its intended niche. Over-broad activation can steer users into prescriptive business/technology guidance they did not request, increasing the chance of irrelevant, biased, or overconfident recommendations.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The skill hard-codes a China-specific market framing and platform set without first checking the user's geography, regulatory environment, or preferred market. This can lead to misaligned compliance, platform, and go-to-market advice, especially for users outside China or in cross-border contexts, and may bias outputs away from user needs.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.