Automator

Security checks across malware telemetry and agentic risk

Overview

This is a clearly described workflow-automation guide with powerful examples, but no hidden code or automatic behavior was found.

Install only if you intend to build OpenClaw automations. For workflows that send messages, post publicly, back up data, or touch production systems, use test environments first, limit credentials, verify recipients and destinations, add human approvals for high-impact steps, and confirm you can pause, stop, and audit every scheduled workflow.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Rogue AgentSelf-Modification, Session Persistence
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)

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill encourages workflows that can send emails, alerts, backups, and publish to production, but it does not prominently warn users about privacy, authorization, destination validation, or operational blast radius. In an automation skill, omitted safety guidance increases the chance that users create workflows which exfiltrate sensitive data, spam recipients, overwrite systems, or make unintended production changes.

Session Persistence

Medium

Category: Rogue Agent
Content: - "Automate my daily report generation" - "Create a workflow that monitors prices and alerts me" - "Set up a multi-step data processing pipeline" - "I need to schedule recurring tasks with dependencies" - "Automate my social media posting across platforms" - "Create an approval workflow for my team" - "Set up automated backups with notifications"
Confidence: 76% confidence
Finding: schedule recurring task

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal