Security audit

Automation Workflows 0.1.0

Security checks across malware telemetry and agentic risk

Overview

This skill is an informational guide for planning no-code business automations and does not contain executable code or hidden access behavior.

Before using the guide to build real automations, review what each connected tool can read or change, use least-privilege accounts, test with sample data, verify destinations and field mappings, and add human approval for customer-facing, payment, contract, or CRM updates.

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 phrases like "automate," "automation," and "save time," which are likely to match many unrelated user requests. This can cause unintended invocation of the skill in contexts where automation advice is inappropriate, increasing the chance of irrelevant or risky guidance being surfaced without sufficient user intent.

Missing User Warnings

Medium

Confidence: 88% confidence
Finding: The skill gives detailed instructions for moving customer, payment, CRM, contract, and usage data across third-party tools, but it does not warn about data minimization, consent, access control, or verification of destinations. In practice, this omission can lead users to build automations that leak sensitive business or customer information, propagate incorrect data, or trigger actions on the wrong records or systems.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.