ClawHub

Automation Workflows Conflict

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only guide for no-code business automations, with expected privacy considerations but no code or hidden behavior.

Before installing or following this skill, verify the publisher/version because the packaged metadata and registry metadata do not fully match. When building automations, use test data first, sync only necessary fields, grant the smallest useful OAuth scopes, review vendor retention and sharing settings, and keep human approval for customer messages, public posts, invoices, payment-related updates, or sensitive personal data.

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
95% confidence
Finding
The trigger phrases are broad enough to match many normal user requests about saving time or reducing manual work, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance that users are routed into automation guidance when they did not explicitly ask for cross-tool workflow design, potentially leading to unnecessary handling of operational or customer data.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill repeatedly recommends connecting forms, CRMs, email tools, accounting software, calendars, Slack, and databases, but it does not warn that these automations may transfer customer, payment, and business data across third-party platforms. Without explicit privacy and compliance guidance, users may implement workflows that expose sensitive data more broadly than intended or violate contractual, regulatory, or least-privilege requirements.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal