ClawHub
Back to skill

Security audit

Automation Workflows

Security checks across malware telemetry and agentic risk

Overview

This skill is a workflow-planning guide for business automations and does not install code, run commands, persist processes, or hide data access.

Before using the advice to build real automations, review what customer, payment, CRM, and usage fields will flow between vendors; grant the minimum permissions needed; avoid putting sensitive details in Slack or email alerts; and document how to disable or audit each workflow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger phrases include very broad everyday terms such as 'automate', 'automation', 'save time', and 'reduce manual work', which can cause the skill to activate in contexts far beyond its intended scope. Over-broad activation is dangerous because it can route unrelated user requests into workflow-building guidance that may encourage connecting external tools and moving data without the user explicitly asking for that level of action.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill repeatedly recommends moving customer, payment, usage, and CRM data across third-party services, but it does not warn about consent, least-privilege access, data minimization, retention, or regulatory/privacy obligations. This is risky because users may implement automations that expose sensitive business or customer data to multiple vendors, webhooks, logs, and notification channels without understanding the security and privacy consequences.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.