Security audit

Work Productivity Gog Google Workflow Helper

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation wording but no hidden code, credential access, persistence, or destructive behavior.

Before installing, be aware this skill may be selected for ordinary Google Workspace or CLI help because its triggers are broad. Review whether you want implicit invocation enabled; otherwise the behavior is proportionate for a workflow-helper skill.

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 (8)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger sentences are highly generic and can match many unrelated requests, increasing the chance this skill activates outside its intended scope. In an agent ecosystem, overbroad activation can cause inappropriate tool selection, context confusion, or accidental invocation of workflow logic for tasks involving Gmail, Calendar, Drive, or other sensitive productivity domains.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are broad, natural-language prompts that could match ordinary user requests and cause the skill to activate unintentionally. In an agent ecosystem, accidental invocation can route tasks into the wrong workflow, expose unnecessary context, or cause actions to be taken under incorrect assumptions.

Vague Triggers

High

Confidence: 95% confidence
Finding: The skill description is broad enough to match many ordinary requests involving Google, CLI, productivity, workflows, or implementation help. That increases the chance of unintended invocation, causing this skill to intercept prompts outside its intended scope and potentially override more appropriate or safer skills.

Vague Triggers

High

Confidence: 98% confidence
Finding: The listed keywords and example triggers are highly generic, including terms such as 'google', 'workspace', 'cli', 'gmail', 'calendar', and 'bug fix', which are common across many unrelated tasks. In a skill-routing system, this can cause excessive or incorrect activation, leading to prompt hijacking at the skill-selection layer and reducing the reliability and safety of agent behavior.

Vague Triggers

High

Confidence: 95% confidence
Finding: The trigger keywords are extremely broad and include common terms like "google", "workspace", "cli", "gmail", and "calendar", which can cause the skill to activate for many unrelated user requests. Over-broad activation increases the chance of misrouting user tasks, overshadowing more appropriate skills, and producing confusing or unsafe workflow guidance in contexts the skill was not designed for.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The description says to use the skill for broad categories such as work-productivity, gog, google, workspace, and CLI, or whenever practical workflow or analysis help is needed, but it does not clearly define boundaries. This ambiguity can cause the system or operators to invoke the skill outside its intended scope, reducing reliability and potentially exposing users to irrelevant or incomplete guidance.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The default prompt trigger phrase is broad and includes generic language like 'help me' and common workplace terms, which can cause the skill to be invoked during ordinary conversation without the user intentionally selecting it. Because implicit invocation is enabled, this increases the chance of unintentional routing, prompt injection exposure, or execution of the wrong workflow in benign user interactions.

Vague Triggers

High

Confidence: 95% confidence
Finding: The trigger sentences are broad, generic, and include common phrases like 'Help me' and 'I need a practical workflow', which can cause the skill to activate for loosely related requests. In an agent-routing context, overly broad matching can misroute user tasks, unexpectedly inject this skill's workflow into unrelated conversations, and reduce the reliability of downstream safety and task selection behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.