Security audit

Work Productivity Gog Google Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation wording, but it does not contain executable code, credential handling, persistence, or hidden privileged behavior.

Install only if you want a lightweight workflow/planning helper. Review or narrow the activation keywords if your environment auto-loads skills, because generic Google and productivity terms may invoke it more often than intended.

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 (10)

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 general requests for workflows or analysis, which can cause the skill to activate outside its intended scope. Over-broad routing increases the chance that unrelated user tasks are handled by this skill, leading to incorrect behavior, prompt-scope confusion, or accidental exposure of context to an unnecessary skill.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The keyword list contains several ambiguous high-frequency terms such as 'google', 'workspace', 'cli', 'gmail', 'calendar', and 'bug fix' without scope constraints. In a skill-routing system, these generic triggers can cause frequent unintended invocation, increasing the attack surface for prompt hijacking, skill misuse, and erroneous delegation of sensitive workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentences and keywords are broad enough to match ordinary requests about work productivity, Google Workspace, CLI, Gmail, Calendar, or bug fixes, which can cause this skill to activate outside its intended scope. Over-broad activation can route unrelated user requests into a workflow shaped by external demand signals rather than the user's actual need, increasing the risk of incorrect handling, privilege misuse, or unexpected access to connected Google/Workspace contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger examples are broad, natural-language phrases that could match ordinary user requests without strong scoping or explicit opt-in. In an agent ecosystem, this can cause unintended activation of the skill for unrelated tasks, leading to confused execution, inappropriate access to Google Workspace-related contexts, or unsafe delegation to instructions the user did not intend to invoke.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad and include generic terms like work-productivity, google, workspace, and cli, which can cause the skill to activate in unrelated contexts. In an agent ecosystem, ambiguous invocation increases the chance of misrouting user requests, unintended execution of the wrong workflow, or exposing actions and guidance in contexts the user did not intend.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger phrases are written in vague, catch-all language and do not define clear boundaries for when the skill should or should not be used. This reinforces over-triggering behavior and makes it more likely that orchestration systems or authors copy permissive patterns that route unrelated user requests into this skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: 文件名和正文均表明这是 zh-CN 中文版本，但文档中未说明语言是可选项，也未向用户提供语言/区域选择。按规则，若技能强制特定语言而没有用户 opt-in 或明确的地域合规理由，属于自然语言政策风险。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords are overly broad and include generic terms like "google", "workspace", and "cli", which can cause the skill to activate for routine or unrelated requests. This increases the chance of accidental invocation, context hijacking, or the model applying this workflow when a more appropriate skill should handle the task.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The default prompt contains a very broad invocation phrase tied to common terms like work productivity, Google, workflow, and practical help, which can cause the skill to be invoked during ordinary user requests that were not meant to call this specific skill. Because implicit invocation is enabled, this increases the chance of unintended routing, prompt injection exposure, or the skill influencing tasks outside its intended scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This file is presented as a Chinese README, but key user-facing descriptive content is written in English. That can amount to an implicit language policy constraint without user opt-in, especially for users expecting a fully zh-CN experience.
Content: No source excerpt is available for this finding.