ClawHub
Back to skill

Security audit

Automation Workflows

Security checks across malware telemetry and agentic risk

Overview

This is a coherent instruction-only playbook for building no-code automations, with expected but important privacy and connector-scope considerations.

Before using this skill to implement automations, review every data flow, grant the minimum connector permissions, avoid sending regulated or unnecessary customer data to extra tools, protect webhooks and API tokens, and test workflows with dummy data before enabling them on real business systems.

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 phrases are broad and include very common business terms such as 'save time' and 'automation', which can cause the skill to activate in situations where the user did not intend to invoke workflow-building guidance. Over-broad activation increases the chance of unsolicited operational advice being applied to sensitive business processes without appropriate user confirmation.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill repeatedly recommends workflows that transfer customer, payment, CRM, usage, and communication data across multiple third-party services, but it does not warn about privacy, consent, data minimization, retention, or misconfiguration risks. In this context, the missing safeguards make it easier for users to create automations that expose personal or business-sensitive data to unnecessary systems or audiences.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.