ClawHub
Back to skill

Security audit

Private Domain Operator

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only WeCom private-domain operations advisor with no install steps, code execution, credential requests, or hidden data access.

Reasonable to install as a planning and advisory skill. Before connecting it to real WeCom, SCRM, Mini Program, payment, or messaging systems, require human approval for outbound messages, purchases, group changes, and customer-data processing, and verify compliance with platform rules and privacy law.

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
95% confidence
Finding
The activation guidance is broad enough that merely mentioning the agent's name or specialty could cause unintended invocation in unrelated conversations. This creates a prompt-routing and least-privilege problem: the skill may activate without clear user intent, leading to inappropriate authority, context takeover, or unexpected domain-specific instructions being injected into the session.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.