Security audit

Work Productivity Gog Google Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a simple workflow-guidance skill with broad activation text, but it does not contain code, credential handling, persistence, or hidden actions.

Before installing, be aware that this skill may be invoked too broadly because of generic trigger terms and implicit invocation. It appears safe from a security standpoint, but users who manage many skills may prefer tighter activation wording to avoid irrelevant workflow guidance appearing in unrelated tasks.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description is broad enough to match common terms like 'google', 'workspace', 'cli', and generic requests for workflows or analysis, which can cause the skill to activate in many unrelated contexts. This increases the chance of misrouting user requests, injecting irrelevant instructions into conversations, or overshadowing more appropriate skills, especially in automated skill-selection systems.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The keyword list includes highly ambiguous terms such as 'google', 'workspace', 'cli', and 'bug fix', which are broad enough to match a large volume of unrelated requests. In a trigger-based routing system, this can lead to accidental invocation, inappropriate context injection, and degraded security or reliability if the wrong skill handles sensitive tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords include broad, everyday terms such as "google", "workspace", and "cli", which can cause the skill to activate for many unrelated requests. This creates routing confusion and may surface the wrong workflow guidance in contexts involving sensitive productivity data or unrelated Google products, reducing reliability and increasing the chance of unsafe overreach.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence is broad enough to match ordinary user phrasing about getting help or practical workflows, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overbroad activation can route unrelated requests into this skill, creating prompt-scope confusion, unintended tool use, or unsafe handling of tasks involving Google Workspace or adjacent automation contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases are generic and expansive, matching common terms like "google," "workspace," "cli," and broad requests for workflows or bug fixes. This can cause unintended activation in unrelated contexts, increasing the chance that the skill intercepts tasks it was not designed to handle and influences agent behavior outside its intended scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad and include generic terms like "google", "workspace", and "cli", which can cause the skill to activate outside the author’s intended scope. In an agent ecosystem, over-broad activation can route unrelated user requests into this skill, leading to incorrect actions, confusing task hijacking, or unsafe workflow guidance being applied in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The example trigger sentences repeat vague demand language instead of demonstrating concrete, bounded use cases, reinforcing loose activation criteria. This makes it more likely that downstream users or routing systems will invoke the skill for broad productivity requests outside its intended scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: 文件名和正文以 zh-CN 中文版本呈现，但文档中未说明这是可选语言版本、也未提供用户语言选择或适用范围说明。根据规则，若技能强制特定语言或地区设置而无用户选择或明确正当理由，属于自然语言策略问题。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description says to use the skill when a user asks for broad categories like work-productivity, google, workspace, or practical support, without clearly defining exclusions or required context. Ambiguous activation logic can cause unintended invocation, leading the agent to apply this skill where it is not appropriate and potentially mishandle user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt uses very broad, everyday phrasing such as helping with work productivity, workflows, and practical support, which overlaps with many normal user requests. In combination with implicit invocation, this broad wording can cause the skill to be selected too often, making prompt routing easier to manipulate and increasing the chance of unintended behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill enables implicit invocation while providing no narrowly scoped trigger conditions, which increases the chance the agent is auto-selected for loosely related requests. Because this skill targets broad productivity and workflow assistance, accidental invocation could cause unintended routing, context mixing, or overbroad application in user conversations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This trigger remains ambiguous because it describes a broad problem area rather than a precise activation condition, so the skill may be invoked for loosely related productivity requests. That increases the chance of misrouting, unnecessary context exposure, or the agent applying this workflow in situations where a different skill or safer baseline behavior would be more appropriate.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This is a zh-CN README, but the main behavior description and all trigger phrases are written in English. That creates a language-policy concern because Chinese-speaking users are not offered a choice or told that invocation must be in English.
Content: No source excerpt is available for this finding.