ClawHub

Automation Workflows

Security checks across malware telemetry and agentic risk

Overview

This is a no-code automation guidance skill with no executable code, installs, hidden persistence, or direct credential access.

Before implementing these workflows, connect only the minimum app permissions needed, test with dummy or low-risk data first, add human review for payments, CRM status changes, public posts, and customer-facing messages, and keep logs plus rollback steps for automations that modify business records.

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
90% confidence
Finding
The trigger list includes broad, everyday phrases such as 'automate', 'automation', 'save time', and 'reduce manual work', which can cause the skill to activate in contexts where the user did not specifically request workflow-automation guidance. Overbroad invocation increases the chance of inappropriate routing, unnecessary data exposure to the skill context, and unsafe application of automation advice to adjacent tasks.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The skill repeatedly recommends moving lead, client, customer, payment, and usage data across multiple third-party services, but it does not warn about data minimization, consent, retention, access control, or verification safeguards. In practice, this can lead users to automate transfers of sensitive business or customer data in ways that create privacy, compliance, or integrity failures, especially when workflows span email, CRM, spreadsheets, Slack, and accounting tools.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal