Automation Workflows Moss

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only automation guide; its third-party workflow examples need normal privacy and permission care, but the artifacts do not show hidden or unsafe behavior.

Install only if you want a general no-code automation playbook. Before turning on any live workflow, review which fields are copied, avoid sending unnecessary customer or payment data to extra tools, use least-privilege OAuth scopes where available, test with safe data first, and document how to disable each automation.

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: 89% confidence
Finding: The trigger list contains broad, common phrases like "automate," "automation," and "save time," which can cause the skill to activate in contexts where the user did not specifically intend workflow-building guidance. Over-broad invocation increases the chance of accidental routing and inappropriate disclosure of business or customer process details to the skill.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill repeatedly recommends workflows that transfer customer, lead, payment, and usage data across third-party systems without explicit privacy, consent, data-minimization, or compliance safeguards. In practice, this can lead users to implement automations that expose sensitive business and customer data to unnecessary services or violate internal policies and regulatory obligations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal