ClawHub

Automation Workflows Openclaw

Security checks across malware telemetry and agentic risk

Overview

This appears to be a business automation strategy guide, not a skill that secretly runs code or moves data on its own.

Install if you want planning help for business automations. Before using its recommendations on real systems, confirm OAuth scopes or API permissions, limit synced fields, test in a sandbox, and require human approval for payments, customer-facing changes, regulated data, or bulk CRM/account updates.

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
95% confidence
Finding
The trigger phrases include very broad terms like "automate," "automation," and "save time," which can match many ordinary conversations unrelated to workflow tooling. This can cause the skill to activate in unintended contexts, increasing the chance of irrelevant guidance being injected into user sessions and reducing routing precision.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill repeatedly recommends moving customer, payment, CRM, and usage data across third-party services but does not instruct users to validate permissions, minimize shared fields, or review privacy and security implications. In practice, this can lead to overbroad data exposure, accidental writes, and noncompliant handling of sensitive business or customer information.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal