Security audit

Automation Workflow Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a broad automation guide that discloses file, network, command, scheduled, and publishing workflows, but it does not clearly scope or gate those high-impact actions.

Review this skill before installing if you do not want a general-purpose automation assistant. Use it only with explicit user approval for shell commands, file writes or moves, uploads, scheduled jobs, webhooks, and public publishing, and restrict it to known directories and trusted services.

SkillSpector

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 (3)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger keywords include very broad terms such as "builder", "automation", and "workflow", which can cause the skill to be invoked in unrelated contexts. In an agent platform, unintended invocation is risky because this skill advertises read and exec capabilities and may prompt file, network, or command operations when the user did not intend to use it.

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: This section documents powerful capabilities including file operations, network requests, and command execution, but provides no warning about possible system modification, data exfiltration, or destructive effects. In a skill intended for cross-platform automation, omission of such guardrails increases the chance that users or downstream agents will perform unsafe actions without understanding the risk.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The examples normalize workflows that fetch remote data, save files, move files, and upload content without any accompanying validation, confirmation, or warning. Example code strongly shapes agent behavior, so unsafe examples in an automation skill can directly encourage workflows that overwrite data, move sensitive files, or transmit information externally.

Static analysis

No suspicious patterns detected.