ClawHub
Back to skill

Security audit

Business Agent Launchpad

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed setup helper for generating business-agent starter workspaces, with some normal caution needed around broad invocation and CLI install steps.

Install this when you want help creating OpenClaw or Hermes business-agent starter files. Before use, confirm the skill was intentionally selected, approve any global npm install only from the expected project folder, and review generated permission plans carefully before enabling actions involving customer records, HR, legal, finance, CRM/accounting systems, forms, messages, payments, or paid cloud services.

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 manifest describes initialization from "plain work scenarios" and provides a generic default prompt for starting agents, but it does not define specific trigger phrases, scope boundaries, or exclusion conditions. In a manifest with implicit invocation enabled, this broad language increases the chance of matching ordinary business-related requests unintentionally.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.